AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Deep Gamblers: Learning to Abstain with Portfolio Theory

Ziyin Liu, Zhikang Wang, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency, Masahito Ueda

NeurIPS 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Learning from unlabeled and positive-unlabeled data · 34 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
Train with the gambler's loss and an added reservation output instead of standard cross-entropyVGG16 classifier · SVHN, coverage 0.95error percentage: 1.39 -> 1.36Improved
Train with the gambler's loss and an added reservation output instead of standard cross-entropyVGG16 classifier · CIFAR10, coverage 0.95error percentage: 4.16 -> 3.49 ± 0.15Improved
Train with the gambler's loss and an added reservation output instead of standard cross-entropyVGG16 classifier · Cats vs. Dogs, coverage 0.95error percentage: 1.62 -> 1.23 ± 0.12Improved
Train with the gambler's loss and an added reservation output instead of standard cross-entropyVGG16 classifier · SVHN, coverage 1.00error percentage: 3.21 -> 3.24 ± 0.09Hurt
Use the best per-coverage hyperparameter setting rather than the best single modelDeep Gamblers · SVHN, coverage 0.85error percentage: 0.57 ± 0.07 -> 0.66 ± 0.01Hurt
Use the best per-coverage hyperparameter setting rather than the best single modelDeep Gamblers · Cats vs. Dogs, coverage 0.95error percentage: 1.23 ± 0.12 -> 0.88 ± 0.38Improved
Use a lower reward parameter o (ablation)Deep Gamblers · CIFAR10training convergence: nullHurt
Pretrain with cross-entropy before switching to the gambler's loss for low o (ablation)Deep Gamblers · CIFAR10prediction accuracy: nullNo clear effect
Train with a lower o (ablation)Deep Gamblers · various datasets and coverageserror at low coverage: nullMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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