1. Test Modules
  2. Training Characteristics
    1. Input Learning
      1. Gradient Descent
      2. Conjugate Gradient Descent
      3. Limited-Memory BFGS
    2. Results
  3. Results

Target Description: The type Img tile subnet layer.

Report Description: The type Basic.

Subreport: Logs for com.simiacryptus.ref.lang.ReferenceCountingBase

Test Modules

Using Seed 7090151834676062208

Training Characteristics

Input Learning

In this apply, we use a network to learn this target input, given it's pre-evaluated output:

TrainingTester.java:445 executed in 0.01 seconds (0.000 gc):

    return RefArrays.stream(RefUtil.addRef(input_target)).flatMap(RefArrays::stream).map(x -> {
      try {
        return x.prettyPrint();
      } finally {
        x.freeRef();
      }
    }).reduce((a, b) -> a + "\n" + b).orElse("");

Returns

    [
    	[ [ 1.764 ], [ 1.512 ], [ 0.636 ], [ 1.208 ], [ 0.392 ], [ 1.612 ] ],
    	[ [ -1.028 ], [ 1.912 ], [ -0.176 ], [ -0.608 ], [ -1.616 ], [ -1.72 ] ],
    	[ [ 1.032 ], [ 1.048 ], [ 0.092 ], [ 1.524 ], [ -0.384 ], [ 0.3 ] ],
    	[ [ -0.068 ], [ -1.688 ], [ 1.108 ], [ -0.128 ], [ 1.356 ], [ -0.768 ] ],
    	[ [ 0.7 ], [ -0.712 ], [ 0.08 ], [ 1.64 ], [ 0.028 ], [ -0.852 ] ],
    	[ [ 1.556 ], [ 0.788 ], [ 0.496 ], [ 0.048 ], [ 1.556 ], [ -0.804 ] ]
    ]
    [
    	[ [ 0.048 ], [ -0.128 ], [ 1.64 ], [ 1.108 ], [ 0.08 ], [ -0.176 ] ],
    	[ [ -0.712 ], [ -0.608 ], [ 1.912 ], [ 0.392 ], [ 1.356 ], [ 1.208 ] ],
    	[ [ 1.556 ], [ 0.092 ], [ 1.524 ], [ -1.72 ], [ -0.384 ], [ -0.852 ] ],
    	[ [ 0.496 ], [ 0.636 ], [ -1.688 ], [ 0.7 ], [ 0.788 ], [ 1.612 ] ],
    	[ [ 0.028 ], [ 1.048 ], [ -1.616 ], [ -0.804 ], [ -0.068 ], [ -0.768 ] ],
    	[ [ -1.028 ], [ 1.764 ], [ 1.556 ], [ 1.512 ], [ 0.3 ], [ 1.032 ] ]
    ]
    [
    	[ [ -0.768 ], [ 0.028 ], [ 1.524 ], [ 0.788 ], [ 1.032 ], [ -0.608 ] ],
    	[ [ 0.048 ], [ 1.356 ], [ 0.496 ], [ 0.392 ], [ 1.512 ], [ -0.176 ] ],
    	[ [ 0.08 ], [ -0.128 ], [ 1.556 ], [ -0.712 ], [ 1.64 ], [ -0.852 ] ],
    	[ [ 1.108 ], [ -1.72 ], [ 1.208 ], [ 1.612 ], [ 0.3 ], [ -0.804 ] ],
    	[ [ -1.028 ], [ 1.048 ], [ -1.616 ], [ 0.636 ], [ -0.384 ], [ 1.912 ] ],
    	[ [ -1.688 ], [ -0.068 ], [ 0.7 ], [ 0.092 ], [ 1.556 ], [ 1.764 ] ]
    ]
    [
    	[ [ 1.556 ], [ -0.068 ], [ 0.08 ], [ 0.7 ], [ 0.3 ], [ 1.108 ] ],
    	[ [ -1.72 ], [ -1.616 ], [ 1.764 ], [ 1.524 ], [ 1.048 ], [ 0.788 ] ],
    	[ [ 1.032 ], [ -0.608 ], [ 0.092 ], [ 1.64 ], [ -1.688 ], [ 1.912 ] ],
    	[ [ -0.852 ], [ 0.392 ], [ 0.636 ], [ -0.712 ], [ -0.768 ], [ 1.512 ] ],
    	[ [ -1.028 ], [ -0.804 ], [ 1.556 ], [ -0.176 ], [ 0.048 ], [ 0.028 ] ],
    	[ [ 1.208 ], [ 0.496 ], [ -0.128 ], [ -0.384 ], [ 1.356 ], [ 1.612 ] ]
    ]
    [
    	[ [ 0.7 ], [ 0.496 ], [ 1.524 ], [ 1.612 ], [ 1.208 ], [ 1.64 ] ],
    	[ [ -1.72 ], [ -0.128 ], [ -1.616 ], [ 1.764 ], [ -0.804 ], [ 0.636 ] ],
    	[ [ -0.068 ], [ -1.028 ], [ -0.852 ], [ 1.512 ], [ 1.556 ], [ 1.108 ] ],
    	[ [ 1.048 ], [ 0.08 ], [ -0.176 ], [ -0.768 ], [ -0.712 ], [ 0.788 ] ],
    	[ [ 0.392 ], [ 0.048 ], [ 1.556 ], [ -1.688 ], [ 1.356 ], [ 0.3 ] ],
    	[ [ 1.912 ], [ 0.028 ], [ 1.032 ], [ -0.608 ], [ 0.092 ], [ -0.384 ] ]
    ]

Gradient Descent

First, we train using basic gradient descent method apply weak line search conditions.

TrainingTester.java:638 executed in 0.99 seconds (0.000 gc):

    IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
    try {
      iterativeTrainer.setLineSearchFactory(label -> new ArmijoWolfeSearch());
      iterativeTrainer.setOrientation(new GradientDescent());
      iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
      iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
      iterativeTrainer.setMaxIterations(250);
      iterativeTrainer.setTerminateThreshold(0);
      return iterativeTrainer.run();
    } finally {
      iterativeTrainer.freeRef();
    }
Logging
Reset training subject: 3437153354292
BACKPROP_AGG_SIZE = 3
THREADS = 64
SINGLE_THREADED = false
Initialized CoreSettings = {
"backpropAggregationSize" : 3,
"jvmThreads" : 64,
"singleThreaded" : false
}
Reset training subject: 3437193026939
Constructing line search parameters: GD
th(0)=203.7488185162317;dx=-1.8049632000000001E24
New Minimum: 203.7488185162317 > 0.043551365662142724
Armijo: th(2.154434690031884)=0.043551365662142724; dx=-1.8049632000162803E12 evalInputDelta=203.70526715056954
Armijo: th(1.077217345015942)=0.22620886154538328; dx=-1.804963200016343E12 evalInputDelta=203.5226096546863
Armijo: th(0.3590724483386473)=1.2277244405460719; dx=-1.8049632000171719E12 evalInputDelta=202.52109407568562
Armijo: th(0.08976811208466183)=3.6511331687038946; dx=-1.804963200026942E12 evalInputDelta=200.0976853475278
Armijo: th(0.017953622416932366)=6.3239861570606415; dx=-1.8049632000732332E12 evalInputDelta=197.42483235917106
Armijo: th(0.002992270402822061)=7.874755567514524; dx=-1.8049632001751382E12 evalInputDelta=195.87406294871718
Armijo: th(4.2746720040315154E-4)=8.418755620203447; dx=-1.8049632002727354E12 evalInputDelta=195.33006289602824
Armijo: th(5.343340005039394E-5)=8.525048685381933; dx=-1.8049632003020386E12 evalInputDelta=195.22376983084976
Armijo: th(5.9370444500437714E-6)=8.539375149882819; dx=-1.8049632003063706E12 evalInputDelta=195.20944336634886
Armijo: th(5.937044450043771E-7)=8.540999849957691; dx=-1.8049632003068682E12 evalInputDelta=195.207818666274
Armijo: th(5.397313136403428E-8)=8.541164109018299; dx=-1.8049632003069185E12 evalInputDelta=195.2076544072134
Armijo: th(4.4977609470028565E-9)=8.541179167459184; dx=-1.804963200306923E12 evalInputDelta=195.20763934877252
Armijo: th(3.4598161130791205E-10)=8.541711667016804; dx=-1.8049663209035562E12 evalInputDelta=195.20710684921488
Armijo: th(2.4712972236279432E-11)=13.155149426419593; dx=-5.096960001825649E21 evalInputDelta=190.5936690898121
Armijo: th(1.6475314824186289E-12)=130.05387779488768; dx=-9.916825600036221E23 evalInputDelta=73.69494072134401
Armijo: th(1.029707176511643E-13)=203.74881851620037; dx=-1.8049632000000001E24 evalInputDelta=3.1320723792305216E-11
Armijo: th(6.057101038303783E-15)=203.74881851622985; dx=-1.8049632000000001E24 evalInputDelta=1.8474111129762605E-12
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.043551365662142724
Fitness changed from 203.7488185162317 to 0.043551365662142724
Iteration 1 complete. Error: 0.043551365662142724 Total: 0.3450; Orientation: 0.0044; Line Search: 0.2796
th(0)=0.043551365662142724;dx=-6.0478111875764835
New Minimum: 0.043551365662142724 > 0.04355136566214269
WOLFE (weak): th(2.154434690031884E-15)=0.04355136566214269; dx=-6.0478111875764835 evalInputDelta=3.469446951953614E-17
New Minimum: 0.04355136566214269 > 0.04355136566214265
WOLFE (weak): th(4.308869380063768E-15)=0.04355136566214265; dx=-6.0478111875764835 evalInputDelta=7.632783294297951E-17
New Minimum: 0.04355136566214265 > 0.04355136566214249
WOLFE (weak): th(1.2926608140191303E-14)=0.04355136566214249; dx=-6.0478111875764835 evalInputDelta=2.3592239273284576E-16
New Minimum: 0.04355136566214249 > 0.04355136566214176
WOLFE (weak): th(5.1706432560765214E-14)=0.04355136566214176; dx=-6.0478111875764835 evalInputDelta=9.645062526431047E-16
New Minimum: 0.04355136566214176 > 0.04355136566213794
WOLFE (weak): th(2.5853216280382605E-13)=0.04355136566213794; dx=-6.0478111875764835 evalInputDelta=4.78089789979208E-15
New Minimum: 0.04355136566213794 > 0.04355136566211399
WOLFE (weak): th(1.5511929768229563E-12)=0.04355136566211399; dx=-6.047811187576481 evalInputDelta=2.873395965607983E-14
New Minimum: 0.04355136566211399 > 0.043551365661941635
WOLFE (weak): th(1.0858350837760695E-11)=0.043551365661941635; dx=-6.047811187576465 evalInputDelta=2.0108914533523148E-13
New Minimum: 0.043551365661941635 > 0.04355136566053398
WOLFE (weak): th(8.686680670208556E-11)=0.04355136566053398; dx=-6.047811187576331 evalInputDelta=1.6087409182574675E-12
New Minimum: 0.04355136566053398 > 0.04355136564766403
WOLFE (weak): th(7.8180126031877E-10)=0.04355136564766403; dx=-6.047811187575111 evalInputDelta=1.4478696019892823E-11
New Minimum: 0.04355136564766403 > 0.04355136551735572
WOLFE (weak): th(7.818012603187701E-9)=0.04355136551735572; dx=-6.047811187562761 evalInputDelta=1.4478700183229165E-10
New Minimum: 0.04355136551735572 > 0.04355136406948579
WOLFE (weak): th(8.599813863506471E-8)=0.04355136406948579; dx=-6.047811187425539 evalInputDelta=1.5926569368884813E-9
New Minimum: 0.04355136406948579 > 0.04355134655026039
WOLFE (weak): th(1.0319776636207765E-6)=0.04355134655026039; dx=-6.0478111857651555 evalInputDelta=1.9111882333666674E-8
New Minimum: 0.04355134655026039 > 0.043551117207818076
WOLFE (weak): th(1.3415709627070094E-5)=0.043551117207818076; dx=-6.047811164029239 evalInputDelta=2.4845432464865036E-7
New Minimum: 0.043551117207818076 > 0.04354788733034452
WOLFE (weak): th(1.878199347789813E-4)=0.04354788733034452; dx=-6.04781085792088 evalInputDelta=3.4783317982012285E-6
New Minimum: 0.04354788733034452 > 0.04349919718514584
WOLFE (weak): th(0.0028172990216847197)=0.04349919718514584; dx=-6.047806244056229 evalInputDelta=5.2168476996884705E-5
New Minimum: 0.04349919718514584 > 0.04271833641509891
WOLFE (weak): th(0.045076784346955515)=0.04271833641509891; dx=-6.047732427501336 evalInputDelta=8.33029247043815E-4
New Minimum: 0.04271833641509891 > 0.03165028409771076
WOLFE (weak): th(0.7663053338982437)=0.03165028409771076; dx=-6.0467514434826075 evalInputDelta=0.011901081564431967
New Minimum: 0.03165028409771076 > 0.0030966742098258457
WOLFE (weak): th(13.793496010168386)=0.0030966742098258457; dx=-6.045534032233926 evalInputDelta=0.04045469145231688
New Minimum: 0.0030966742098258457 > 0.0
WOLFE (weak): th(262.07642419319933)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
WOLFE (weak): th(5241.528483863986)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
Armijo: th(110072.09816114372)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
Armijo: th(57656.813322503855)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
Armijo: th(31449.17090318392)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
Armijo: th(18345.349693523953)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
Armijo: th(11793.43908869397)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
Armijo: th(8517.483786278977)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
WOLFE (weak): th(6879.506135071482)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
Armijo: th(7698.49496067523)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
Armijo: th(7289.0005478733565)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
WOLFE (weak): th(7084.253341472419)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
WOLFE (weak): th(7186.6269446728875)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
Armijo: th(7237.813746273122)=0.0; dx=-6.045485113902158 evalInputDelta=0.043551365662142724
mu ~= nu (7186.6269446728875): th(262.07642419319933)=0.0
Fitness changed from 0.043551365662142724 to 0.0
Iteration 2 complete. Error: 0.0 Total: 0.2706; Orientation: 0.0014; Line Search: 0.2607
th(0)=0.0;dx=-6.043728000000001
Armijo: th(15538.257704440777)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(7769.128852220389)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(2589.709617406796)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(647.427404351699)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(129.4854808703398)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(21.58091347838997)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(3.082987639769996)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(0.3853734549712495)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(0.04281927277458328)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(0.004281927277458328)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(3.892661161325752E-4)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(3.2438843011047935E-5)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(2.4952956162344564E-6)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(1.7823540115960404E-7)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(1.1882360077306936E-8)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(7.426475048316835E-10)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(4.3685147343040204E-11)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(2.4269526301689004E-12)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(1.2773434895625792E-13)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Armijo: th(6.386717447812896E-15)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
MIN ALPHA (3.0412940227680456E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.3607; Orientation: 0.0008; Line Search: 0.3540
Iteration 3 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 3
Final threshold in iteration 3: 0.0 (> 0.0) after 0.977s (< 30.000s)

Returns

    0.0

Training Converged

Conjugate Gradient Descent

First, we use a conjugate gradient descent method, which converges the fastest for purely linear functions.

TrainingTester.java:603 executed in 1.29 seconds (0.000 gc):

    IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
    try {
      iterativeTrainer.setLineSearchFactory(label -> new QuadraticSearch());
      iterativeTrainer.setOrientation(new GradientDescent());
      iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
      iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
      iterativeTrainer.setMaxIterations(250);
      iterativeTrainer.setTerminateThreshold(0);
      return iterativeTrainer.run();
    } finally {
      iterativeTrainer.freeRef();
    }
Logging
Reset training subject: 3438137543261
Reset training subject: 3438144580836
Constructing line search parameters: GD
F(0.0) = LineSearchPoint{point=PointSample{avg=203.7488185162317}, derivative=-1.8049632000000001E24}
New Minimum: 203.7488185162317 > 9.313085920809598
F(1.0E-10) = LineSearchPoint{point=PointSample{avg=9.313085920809598}, derivative=-2.156800018087582E20}, evalInputDelta = -194.4357325954221
New Minimum: 9.313085920809598 > 8.541180323364141
F(7.000000000000001E-10) = LineSearchPoint{point=PointSample{avg=8.541180323364141}, derivative=-1.8049632003069233E12}, evalInputDelta = -195.20763819286756
New Minimum: 8.541180323364141 > 8.541179045031834
F(4.900000000000001E-9) = LineSearchPoint{point=PointSample{avg=8.541179045031834}, derivative=-1.8049632003069229E12}, evalInputDelta = -195.20763947119985
New Minimum: 8.541179045031834 > 8.54117009675178
F(3.430000000000001E-8) = LineSearchPoint{point=PointSample{avg=8.54117009675178}, derivative=-1.8049632003069202E12}, evalInputDelta = -195.2076484194799
New Minimum: 8.54117009675178 > 8.541107461050377
F(2.4010000000000004E-7) = LineSearchPoint{point=PointSample{avg=8.541107461050377}, derivative=-1.804963200306901E12}, evalInputDelta = -195.2077110551813
New Minimum: 8.541107461050377 > 8.54066912178195
F(1.6807000000000003E-6) = LineSearchPoint{point=PointSample{avg=8.54066912178195}, derivative=-1.8049632003067666E12}, evalInputDelta = -195.20814939444975
New Minimum: 8.54066912178195 > 8.537606151631877
F(1.1764900000000001E-5) = LineSearchPoint{point=PointSample{avg=8.537606151631877}, derivative=-1.8049632003058303E12}, evalInputDelta = -195.21121236459982
New Minimum: 8.537606151631877 > 8.516424610266276
F(8.235430000000001E-5) = LineSearchPoint{point=PointSample{avg=8.516424610266276}, derivative=-1.804963200299478E12}, evalInputDelta = -195.2323939059654
New Minimum: 8.516424610266276 > 8.379233970640733
F(5.764801000000001E-4) = LineSearchPoint{point=PointSample{avg=8.379233970640733}, derivative=-1.8049632002629814E12}, evalInputDelta = -195.36958454559095
New Minimum: 8.379233970640733 > 7.705361872251009
F(0.004035360700000001) = LineSearchPoint{point=PointSample{avg=7.705361872251009}, derivative=-1.8049632001557517E12}, evalInputDelta = -196.04345664398068
New Minimum: 7.705361872251009 > 5.696450486186289
F(0.028247524900000005) = LineSearchPoint{point=PointSample{avg=5.696450486186289}, derivative=-1.8049632000557388E12}, evalInputDelta = -198.05236803004541
New Minimum: 5.696450486186289 > 2.217225827747974
F(0.19773267430000002) = LineSearchPoint{point=PointSample{avg=2.217225827747974}, derivative=-1.8049632000194468E12}, evalInputDelta = -201.53159268848373
New Minimum: 2.217225827747974 > 0.15268616341259902
F(1.3841287201) = LineSearchPoint{point=PointSample{avg=0.15268616341259902}, derivative=-1.804963200016316E12}, evalInputDelta = -203.5961323528191
New Minimum: 0.15268616341259902 > 0.0036719418822635337
F(9.688901040700001) = LineSearchPoint{point=PointSample{avg=0.0036719418822635337}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.74514657434943
New Minimum: 0.0036719418822635337 > 0.0
F(67.8223072849) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(474.7561509943) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(3323.2930569601003) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(23263.0513987207) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(162841.3597910449) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(1139889.5185373144) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(7979226.6297612) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(5.58545864083284E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(3.909821048582988E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(2.7368747340080914E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
F(1.915812313805664E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
0.0 <= 203.7488185162317
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-1.8049632000162717E12}, evalInputDelta = -203.7488185162317
Right bracket at 1.0E10
Converged to right
Fitness changed from 203.7488185162317 to 0.0
Iteration 1 complete. Error: 0.0 Total: 0.5525; Orientation: 0.0008; Line Search: 0.5141
F(0.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}
F(1.0E10) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
0.0 <= 0.0
F(5.0E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 5.0E9
F(2.5E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 2.5E9
F(1.25E9) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 1.25E9
F(6.25E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 6.25E8
F(3.125E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 3.125E8
F(1.5625E8) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 1.5625E8
F(7.8125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 7.8125E7
F(3.90625E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 3.90625E7
F(1.953125E7) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 1.953125E7
F(9765625.0) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 9765625.0
F(4882812.5) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Right bracket at 4882812.5
F(2441406.25) = LineSearchPoint{point=PointSample{avg=0.0}, derivative=-6.043728000000001}, evalInputDelta = 0.0
Loops = 12
Fitness changed from 0.0 to 0.0
Static Iteration Total: 0.7344; Orientation: 0.0008; Line Search: 0.6951
Iteration 2 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 2
Final threshold in iteration 2: 0.0 (> 0.0) after 1.288s (< 30.000s)

Returns

    0.0

Training Converged

Limited-Memory BFGS

Next, we apply the same optimization using L-BFGS, which is nearly ideal for purely second-order or quadratic functions.

TrainingTester.java:674 executed in 8.37 seconds (0.106 gc):

    IterativeTrainer iterativeTrainer = new IterativeTrainer(trainable.addRef());
    try {
      iterativeTrainer.setLineSearchFactory(label -> new ArmijoWolfeSearch());
      iterativeTrainer.setOrientation(new LBFGS());
      iterativeTrainer.setMonitor(TrainingTester.getMonitor(history));
      iterativeTrainer.setTimeout(30, TimeUnit.SECONDS);
      iterativeTrainer.setIterationsPerSample(100);
      iterativeTrainer.setMaxIterations(250);
      iterativeTrainer.setTerminateThreshold(0);
      return iterativeTrainer.run();
    } finally {
      iterativeTrainer.freeRef();
    }
Logging
Reset training subject: 3439429663330
Reset training subject: 3439435954380
Adding measurement 727f1d7c to history. Total: 0
LBFGS Accumulation History: 1 points
Constructing line search parameters: GD
Non-optimal measurement 203.7488185162317 < 203.7488185162317. Total: 1
th(0)=203.7488185162317;dx=-1.8049632000000001E24
Adding measurement 57d6ce5c to history. Total: 1
New Minimum: 203.7488185162317 > 0.043551365662142724
Armijo: th(2.154434690031884)=0.043551365662142724; dx=-1.8049632000162803E12 evalInputDelta=203.70526715056954
Non-optimal measurement 0.22620886154538328 < 0.043551365662142724. Total: 2
Armijo: th(1.077217345015942)=0.22620886154538328; dx=-1.804963200016343E12 evalInputDelta=203.5226096546863
Non-optimal measurement 1.2277244405460719 < 0.043551365662142724. Total: 2
Armijo: th(0.3590724483386473)=1.2277244405460719; dx=-1.8049632000171719E12 evalInputDelta=202.52109407568562
Non-optimal measurement 3.6511331687038946 < 0.043551365662142724. Total: 2
Armijo: th(0.08976811208466183)=3.6511331687038946; dx=-1.804963200026942E12 evalInputDelta=200.0976853475278
Non-optimal measurement 6.3239861570606415 < 0.043551365662142724. Total: 2
Armijo: th(0.017953622416932366)=6.3239861570606415; dx=-1.8049632000732332E12 evalInputDelta=197.42483235917106
Non-optimal measurement 7.874755567514524 < 0.043551365662142724. Total: 2
Armijo: th(0.002992270402822061)=7.874755567514524; dx=-1.8049632001751382E12 evalInputDelta=195.87406294871718
Non-optimal measurement 8.418755620203447 < 0.043551365662142724. Total: 2
Armijo: th(4.2746720040315154E-4)=8.418755620203447; dx=-1.8049632002727354E12 evalInputDelta=195.33006289602824
Non-optimal measurement 8.525048685381933 < 0.043551365662142724. Total: 2
Armijo: th(5.343340005039394E-5)=8.525048685381933; dx=-1.8049632003020386E12 evalInputDelta=195.22376983084976
Non-optimal measurement 8.539375149882819 < 0.043551365662142724. Total: 2
Armijo: th(5.9370444500437714E-6)=8.539375149882819; dx=-1.8049632003063706E12 evalInputDelta=195.20944336634886
Non-optimal measurement 8.540999849957691 < 0.043551365662142724. Total: 2
Armijo: th(5.937044450043771E-7)=8.540999849957691; dx=-1.8049632003068682E12 evalInputDelta=195.207818666274
Non-optimal measurement 8.541164109018299 < 0.043551365662142724. Total: 2
Armijo: th(5.397313136403428E-8)=8.541164109018299; dx=-1.8049632003069185E12 evalInputDelta=195.2076544072134
Non-optimal measurement 8.541179167459184 < 0.043551365662142724. Total: 2
Armijo: th(4.4977609470028565E-9)=8.541179167459184; dx=-1.804963200306923E12 evalInputDelta=195.20763934877252
Non-optimal measurement 8.541711667016804 < 0.043551365662142724. Total: 2
Armijo: th(3.4598161130791205E-10)=8.541711667016804; dx=-1.8049663209035562E12 evalInputDelta=195.20710684921488
Non-optimal measurement 13.155149426419593 < 0.043551365662142724. Total: 2
Armijo: th(2.4712972236279432E-11)=13.155149426419593; dx=-5.096960001825649E21 evalInputDelta=190.5936690898121
Non-optimal measurement 130.05387779488768 < 0.043551365662142724. Total: 2
Armijo: th(1.6475314824186289E-12)=130.05387779488768; dx=-9.916825600036221E23 evalInputDelta=73.69494072134401
Non-optimal measurement 203.74881851620037 < 0.043551365662142724. Total: 2
Armijo: th(1.029707176511643E-13)=203.74881851620037; dx=-1.8049632000000001E24 evalInputDelta=3.1320723792305216E-11
Non-optimal measurement 203.74881851622985 < 0.043551365662142724. Total: 2
Armijo: th(6.057101038303783E-15)=203.74881851622985; dx=-1.8049632000000001E24 evalInputDelta=1.8474111129762605E-12
Non-optimal measurement 0.043551365662142724 < 0.043551365662142724. Total: 2
MIN ALPHA (3.3650561323909904E-16): th(2.154434690031884)=0.043551365662142724
Fitness changed from 203.7488185162317 to 0.043551365662142724
Iteration 1 complete. Error: 0.043551365662142724 Total: 0.3751; Orientation: 0.0042; Line Search: 0.2630
Non-optimal measurement 0.043551365662142724 < 0.043551365662142724. Total: 2
LBFGS Accumulation History: 2 points
Non-optimal measurement 0.043551365662142724 < 0.043551365662142724. Total: 2
th(0)=0.043551365662142724;dx=-6.0478111875764835
Adding measurement 5e305c53 to history. Total: 2
New Minimum: 0.043551365662142724 > 0.04355136566214269
WOLFE (weak): th(2.154434690031884E-15)=0.04355136566214269; dx=-6.0478111875764835 evalInputDelta=3.469446951953614E-17
Adding measurement 23d9690e to history. Total: 3
New Minimum: 0.04355136566214269 > 0.04355136566214265
WOLFE (weak): th(4.308869380063768E-15)=0.04355136566214265; dx=-6.0478111875764835 evalInputDelta=7.632783294297951E-17
Adding measurement 3fc53740 to history. Total: 4
New Minimum: 0.04355136566214265 > 0.04355136566214249
WOLFE (weak): th(1.2926608140191303E-14)=0.04355136566214249; dx=-6.0478111875764835 evalInputDelta=2.3592239273284576E-16
Adding measurement 108e629b to history. Total: 5
New Minimum: 0.04355136566214249 > 0.04355136566214176
WOLFE (weak): th(5.1706432560765214E-14)=0.04355136566214176; dx=-6.0478111875764835 evalInputDelta=9.645062526431047E-16
Adding measurement 3a171df to history. Total: 6
New Minimum: 0.04355136566214176 > 0.04355136566213794
WOLFE (weak): th(2.5853216280382605E-13)=0.04355136566213794; dx=-6.0478111875764835 evalInputDelta=4.78089789979208E-15
Adding measurement 24cb70a3 to history. Total: 7
New Minimum: 0.04355136566213794 > 0.04355136566211399
WOLFE (weak): th(1.5511929768229563E-12)=0.04355136566211399; dx=-6.047811187576481 evalInputDelta=2.873395965607983E-14
Adding measurement 1af24ac3 to history. Total: 8
New Minimum: 0.04355136566211399 > 0.043551365661941635
WOLFE (weak): th(1.0858350837760695E-11)=0.043551365661941635; dx=-6.047811187576465 evalInputDelta=2.0108914533523148E-13
Adding measurement 53c3820 to history. Total: 9
New Minimum: 0.043551365661941635 > 0.04355136566053398
WOLFE (weak): th(8.686680670208556E-11)=0.04355136566053398; dx=-6.047811187576331 evalInputDelta=1.6087409182574675E-12
Adding measurement 1e681da7 to history. Total: 10
New Minimum: 0.04355136566053398 > 0.04355136564766403
WOLFE (weak): th(7.8180126031877E-10)=0.04355136564766403; dx=-6.047811187575111 evalInputDelta=1.4478696019892823E-11
Adding measurement 2752ab8 to history. Total: 11
New Minimum: 0.04355136564766403 > 0.04355136551735572
WOLFE (weak): th(7.818012603187701E-9)=0.04355136551735572; dx=-6.047811187562761 evalInputDelta=1.4478700183229165E-10
Adding measurement 46a67f5f to history. Total: 12
New Minimum: 0.04355136551735572 > 0.04355136406948579
WOLFE (weak): th(8.599813863506471E-8)=0.04355136406948579; dx=-6.047811187425539 evalInputDelta=1.5926569368884813E-9
Adding measurement 76d1f673 to history. Total: 13
New Minimum: 0.04355136406948579 > 0.04355134655026039
WOLFE (weak): th(1.0319776636207765E-6)=0.04355134655026039; dx=-6.0478111857651555 evalInputDelta=1.9111882333666674E-8
Adding measurement 199a3fc3 to history. Total: 14
New Minimum: 0.04355134655026039 > 0.043551117207818076
WOLFE (weak): th(1.3415709627070094E-5)=0.043551117207818076; dx=-6.047811164029239 evalInputDelta=2.4845432464865036E-7
Adding measurement 669531d1 to history. Total: 15
New Minimum: 0.043551117207818076 > 0.04354788733034452
WOLFE (weak): th(1.878199347789813E-4)=0.04354788733034452; dx=-6.04781085792088 evalInputDelta=3.4783317982012285E-6
Adding measurement 63341250 to history. Total: 16
New Minimum: 0.04354788733034452 > 0.04349919718514584
WOLFE (weak): th(0.0028172990216847197)=0.04349919718514584; dx=-6.047806244056229 evalInputDelta=5.2168476996884705E-5
Adding measurement ee62ccb to history. Total: 17
New Minimum: 0.04349919718514584 > 0.04271833641509891
WOLFE (weak): th(0.045076784346955515)=0.04271833641509891; dx=-6.047732427501336 evalInputDelta=8.33029247043815E-4
Adding measurement 25fed177 to history. Total: 18
New Minimum: 0.04271833641509891 > 0.03165028409771076
WOLFE (weak): th(0.7663053338982437)=0.03165028409771076; dx=-6.0467514434826075 evalInputDelta=0.011901081564431967
Adding measurement 29f10235 to history. Total: 19
New Minimum: 0.03165028409771076 > 0.0030966742098258457
WOLFE (weak): th(13.793496010168386)=0.0030966742098258457; dx=-6.045534032233926 evalInputDelta=0.04045469145231688
Adding measurement 46a9d3e

...skipping 9834 bytes...

c9ad-c78f-4efd-a575-251cc691aa06 = 1.000/1.000e+00, 95fc2be6-ddff-40b8-8405-3ad9ed76a828 = 1.000/1.000e+00, ed951bdf-0694-4a99-9f68-8c104678ab07 = 1.000/1.000e+00, e5cafd6b-9d0a-4c66-82a8-f9762d160fa7 = 1.000/1.000e+00, a5135b3d-d85d-4f39-ba2e-d8198a0794d4 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0030966742098258457, 0.03165028409771076, 0.04271833641509891, 0.04349919718514584, 0.04354788733034452, 0.043551117207818076, 0.04355134655026039, 0.04355136406948579, 0.04355136551735572, 0.04355136564766403
Rejected: LBFGS Orientation magnitude: 1.340e+04, gradient 2.458e+00, dot -0.988; [d524c9ad-c78f-4efd-a575-251cc691aa06 = 1.000/1.000e+00, a5135b3d-d85d-4f39-ba2e-d8198a0794d4 = 1.000/1.000e+00, e5cafd6b-9d0a-4c66-82a8-f9762d160fa7 = 1.000/1.000e+00, 95fc2be6-ddff-40b8-8405-3ad9ed76a828 = 1.000/1.000e+00, ed951bdf-0694-4a99-9f68-8c104678ab07 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0030966742098258457, 0.03165028409771076, 0.04271833641509891, 0.04349919718514584, 0.04354788733034452, 0.043551117207818076, 0.04355134655026039, 0.04355136406948579, 0.04355136551735572
Rejected: LBFGS Orientation magnitude: 1.340e+04, gradient 2.458e+00, dot -0.988; [a5135b3d-d85d-4f39-ba2e-d8198a0794d4 = 1.000/1.000e+00, e5cafd6b-9d0a-4c66-82a8-f9762d160fa7 = 1.000/1.000e+00, d524c9ad-c78f-4efd-a575-251cc691aa06 = 1.000/1.000e+00, 95fc2be6-ddff-40b8-8405-3ad9ed76a828 = 1.000/1.000e+00, ed951bdf-0694-4a99-9f68-8c104678ab07 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0030966742098258457, 0.03165028409771076, 0.04271833641509891, 0.04349919718514584, 0.04354788733034452, 0.043551117207818076, 0.04355134655026039, 0.04355136406948579
Rejected: LBFGS Orientation magnitude: 1.340e+04, gradient 2.458e+00, dot -0.988; [e5cafd6b-9d0a-4c66-82a8-f9762d160fa7 = 1.000/1.000e+00, ed951bdf-0694-4a99-9f68-8c104678ab07 = 1.000/1.000e+00, a5135b3d-d85d-4f39-ba2e-d8198a0794d4 = 1.000/1.000e+00, 95fc2be6-ddff-40b8-8405-3ad9ed76a828 = 1.000/1.000e+00, d524c9ad-c78f-4efd-a575-251cc691aa06 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0030966742098258457, 0.03165028409771076, 0.04271833641509891, 0.04349919718514584, 0.04354788733034452, 0.043551117207818076, 0.04355134655026039
Rejected: LBFGS Orientation magnitude: 1.693e+04, gradient 2.458e+00, dot -0.971; [e5cafd6b-9d0a-4c66-82a8-f9762d160fa7 = 1.000/1.000e+00, d524c9ad-c78f-4efd-a575-251cc691aa06 = 1.000/1.000e+00, ed951bdf-0694-4a99-9f68-8c104678ab07 = 1.000/1.000e+00, 95fc2be6-ddff-40b8-8405-3ad9ed76a828 = 1.000/1.000e+00, a5135b3d-d85d-4f39-ba2e-d8198a0794d4 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0030966742098258457, 0.03165028409771076, 0.04271833641509891, 0.04349919718514584, 0.04354788733034452, 0.043551117207818076
Rejected: LBFGS Orientation magnitude: 1.694e+04, gradient 2.458e+00, dot -1.000; [e5cafd6b-9d0a-4c66-82a8-f9762d160fa7 = 1.000/1.000e+00, ed951bdf-0694-4a99-9f68-8c104678ab07 = 1.000/1.000e+00, d524c9ad-c78f-4efd-a575-251cc691aa06 = 1.000/1.000e+00, 95fc2be6-ddff-40b8-8405-3ad9ed76a828 = 1.000/1.000e+00, a5135b3d-d85d-4f39-ba2e-d8198a0794d4 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0030966742098258457, 0.03165028409771076, 0.04271833641509891, 0.04349919718514584, 0.04354788733034452
Rejected: LBFGS Orientation magnitude: 1.701e+04, gradient 2.458e+00, dot -1.000; [d524c9ad-c78f-4efd-a575-251cc691aa06 = 1.000/1.000e+00, e5cafd6b-9d0a-4c66-82a8-f9762d160fa7 = 1.000/1.000e+00, a5135b3d-d85d-4f39-ba2e-d8198a0794d4 = 1.000/1.000e+00, 95fc2be6-ddff-40b8-8405-3ad9ed76a828 = 1.000/1.000e+00, ed951bdf-0694-4a99-9f68-8c104678ab07 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0030966742098258457, 0.03165028409771076, 0.04271833641509891, 0.04349919718514584
Rejected: LBFGS Orientation magnitude: 2.184e+04, gradient 2.458e+00, dot -1.000; [a5135b3d-d85d-4f39-ba2e-d8198a0794d4 = 1.000/1.000e+00, ed951bdf-0694-4a99-9f68-8c104678ab07 = 1.000/1.000e+00, 95fc2be6-ddff-40b8-8405-3ad9ed76a828 = 1.000/1.000e+00, e5cafd6b-9d0a-4c66-82a8-f9762d160fa7 = 1.000/1.000e+00, d524c9ad-c78f-4efd-a575-251cc691aa06 = 1.000/1.000e+00]
Orientation rejected. Popping history element from 0.0, 0.0030966742098258457, 0.03165028409771076, 0.04271833641509891
LBFGS Accumulation History: 3 points
Removed measurement 46a9d3e0 to history. Total: 20
Removed measurement 29f10235 to history. Total: 19
Removed measurement 25fed177 to history. Total: 18
Removed measurement ee62ccb to history. Total: 17
Removed measurement 63341250 to history. Total: 16
Removed measurement 669531d1 to history. Total: 15
Removed measurement 199a3fc3 to history. Total: 14
Removed measurement 76d1f673 to history. Total: 13
Removed measurement 46a67f5f to history. Total: 12
Removed measurement 2752ab8 to history. Total: 11
Removed measurement 1e681da7 to history. Total: 10
Removed measurement 53c3820 to history. Total: 9
Removed measurement 1af24ac3 to history. Total: 8
Removed measurement 24cb70a3 to history. Total: 7
Removed measurement 3a171df to history. Total: 6
Removed measurement 108e629b to history. Total: 5
Removed measurement 3fc53740 to history. Total: 4
Removed measurement 23d9690e to history. Total: 3
Adding measurement 79ac8c5 to history. Total: 3
th(0)=0.0;dx=-6.043728000000001
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(15538.257704440777)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(7769.128852220389)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2589.709617406796)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(647.427404351699)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(129.4854808703398)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(21.58091347838997)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.082987639769996)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.3853734549712495)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.04281927277458328)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(0.004281927277458328)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.892661161325752E-4)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(3.2438843011047935E-5)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.4952956162344564E-6)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.7823540115960404E-7)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.1882360077306936E-8)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(7.426475048316835E-10)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(4.3685147343040204E-11)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(2.4269526301689004E-12)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(1.2773434895625792E-13)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
Armijo: th(6.386717447812896E-15)=0.0; dx=-6.043728000000001 evalInputDelta=0.0
Non-optimal measurement 0.0 < 0.0. Total: 4
MIN ALPHA (3.0412940227680456E-16): th(0.0)=0.0
Fitness changed from 0.0 to 0.0
Static Iteration Total: 7.3827; Orientation: 6.8862; Line Search: 0.4899
Iteration 3 failed. Error: 0.0
Previous Error: 0.0 -> 0.0
Optimization terminated 3
Final threshold in iteration 3: 0.0 (> 0.0) after 8.370s (< 30.000s)

Returns

    0.0

Training Converged

TrainingTester.java:576 executed in 0.10 seconds (0.000 gc):

    return TestUtil.compare(title + " vs Iteration", runs);
Logging
Plotting range=[1.0, -2.3609982220516437], [2.0, -0.36099822205164367]; valueStats=DoubleSummaryStatistics{count=2, sum=0.087103, min=0.043551, average=0.043551, max=0.043551}
Plotting 2 points for GD
Only 1 points for CjGD
Plotting 2 points for LBFGS

Returns

Result

TrainingTester.java:579 executed in 0.01 seconds (0.000 gc):

    return TestUtil.compareTime(title + " vs Time", runs);
Logging
Plotting range=[0.0, -2.3609982220516437], [0.612, -0.36099822205164367]; valueStats=DoubleSummaryStatistics{count=2, sum=0.087103, min=0.043551, average=0.043551, max=0.043551}
Plotting 2 points for GD
Only 1 points for CjGD
Plotting 2 points for LBFGS

Returns

Result

Results

TrainingTester.java:350 executed in 0.00 seconds (0.000 gc):

    return grid(inputLearning, modelLearning, completeLearning);

Returns

Result

TrainingTester.java:353 executed in 0.00 seconds (0.000 gc):

    return new ComponentResult(null == inputLearning ? null : inputLearning.value,
        null == modelLearning ? null : modelLearning.value, null == completeLearning ? null : completeLearning.value);

Returns

    {"input":{ "LBFGS": { "type": "Converged", "value": 0.0 }, "CjGD": { "type": "Converged", "value": 0.0 }, "GD": { "type": "Converged", "value": 0.0 } }, "model":null, "complete":null}

LayerTests.java:605 executed in 0.00 seconds (0.000 gc):

    throwException(exceptions.addRef());

Results

detailsresult
{"input":{ "LBFGS": { "type": "Converged", "value": 0.0 }, "CjGD": { "type": "Converged", "value": 0.0 }, "GD": { "type": "Converged", "value": 0.0 } }, "model":null, "complete":null}OK
  {
    "result": "OK",
    "performance": {
      "execution_time": "11.547",
      "gc_time": "0.493"
    },
    "created_on": 1587005456473,
    "file_name": "trainingTest",
    "report": {
      "simpleName": "Basic",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.ImgTileSubnetLayerTest.Basic",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/c9a1867488dc7e77a975f095285b5882c0486db6/src/test/java/com/simiacryptus/mindseye/layers/java/ImgTileSubnetLayerTest.java",
      "javaDoc": "The type Basic."
    },
    "training_analysis": {
      "input": {
        "LBFGS": {
          "type": "Converged",
          "value": 0.0
        },
        "CjGD": {
          "type": "Converged",
          "value": 0.0
        },
        "GD": {
          "type": "Converged",
          "value": 0.0
        }
      }
    },
    "archive": "s3://code.simiacrypt.us/tests/com/simiacryptus/mindseye/layers/java/ImgTileSubnetLayer/Basic/trainingTest/202004165056",
    "id": "8d64aae0-be1f-4370-9af8-f19dbff5c1a5",
    "report_type": "Components",
    "display_name": "Comparative Training",
    "target": {
      "simpleName": "ImgTileSubnetLayer",
      "canonicalName": "com.simiacryptus.mindseye.layers.java.ImgTileSubnetLayer",
      "link": "https://github.com/SimiaCryptus/mindseye-java/tree/c9a1867488dc7e77a975f095285b5882c0486db6/src/main/java/com/simiacryptus/mindseye/layers/java/ImgTileSubnetLayer.java",
      "javaDoc": "The type Img tile subnet layer."
    }
  }