AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Training Deep Networks without Learning Rates Through Coin Betting

Francesco Orabona, Tatiana Tommasi

NeurIPS 2017 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use COCOB-Backprop instead of tuned learning-rate optimizersDeep-network training on MNIST, CIFAR-10, and PTB · MNIST, CIFAR-10, PTBtraining costMixed
Use COCOB-Backprop instead of tuned learning-rate optimizersTwo-layer fully connected network and CNN · MNISTtest error rateMixed
Use COCOB-Backprop instead of tuned learning-rate optimizersTensorFlow CNN · CIFAR-10training costNo clear effect
Use COCOB-Backprop instead of tuned learning-rate optimizersTensorFlow CNN · CIFAR-10test error rate: ~0.008 in error rateNo clear effect
Use COCOB-Backprop instead of tuned learning-rate optimizersMedium LSTM · PTBtraining cost (per-word perplexity)Mixed
Use COCOB-Backprop instead of tuned learning-rate optimizersMedium LSTM · PTBtest cost (per-word perplexity)Mixed
Remove the sigmoid transformation from the parameter update (ablation)COCOB-Backprop · Experiments in the paperempirical resultsImproved
Bound the update denominator below by αL (ablation)COCOB-Backprop · Deep-network traininginitial parameter movementImproved
Return the last iterate instead of an average or a random iterate (ablation)COCOB-Backprop · Deep-network trainingtraining or test performanceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy