AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Robust Bi-Tempered Logistic Loss Based on Bregman Divergences

Ehsan Amid, Manfred K. Warmuth, Rohan Anil, Tomer Koren

NeurIPS 2019 · Learning theory and algorithms › Prediction and decision losses · approach: Consistency of surrogate losses · 27 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
Replace logistic loss with bi-tempered loss (0.5, 4.0)CNN · MNIST, 40% label noisetop-1 accuracy: 97.64 -> 98.56Improved
Replace logistic loss with bi-tempered loss (0.8, 1.2)ResNet-56 · CIFAR-100, 40% label noisetop-1 accuracy: 53.17 -> 62.55Improved
Replace logistic loss with bi-tempered loss (0.9,1.05)ResNet-18 · ImageNet-2012top-1 accuracy: 71.333 -> 71.618Improved
Replace logistic loss with bi-tempered loss (0.9,1.05)ResNet-50 · ImageNet-2012top-1 accuracy: 76.332 -> 76.748Improved
Use a heavy-tailed tempered softmax (t2 = 4) while retaining KL loss (t1 = 1) (ablation)Two-layer network on synthetic small-margin label noise · Synthetic binary classification, small-margin label noiserobustness to label noiseImproved
Use a bounded loss (t1 = 0.2) with vanilla softmax (t2 = 1) (ablation)Two-layer network on synthetic large-margin label noise · Synthetic binary classification, large-margin label noiserobustness to label noiseImproved
Use both bounded loss (t1 = 0.2) and heavy-tailed probabilities (t2 = 4.0) (ablation)Two-layer network on synthetic random label noise · Synthetic binary classification, random label noiserobustness to label noiseImproved

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