AI Paper Atlas

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

Stochastic Loss Function

Qingliang Liu, Jinmei Lai

AAAI 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Loss landscape analysis · 16 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 fixed cross-entropy with stochastic loss function (Gumbel-Softmax loss selection)ResNet-20 · CIFAR-10accuracy: 0.9125 -> 0.9302Improved
replace fixed cross-entropy with SLFDAC · ImageNet-10 clusteringACC: 0.5272 -> 0.7345Improved
replace C-E loss with SLFTransformer · IWSLT-14 De-EnBLEU: 34.01 -> 35.53Improved
learn YOLO loss weights with SLFYOLO · PASCAL VOC 2007mAP: 63.4 -> 65.4Improved
replace C-E loss with SLFChebNets · DPP4squared correlation: 0.2650 -> 0.2793Improved
use Gumbel-Softmax selection instead of softmax over all losses (ablation)SLF · CIFAR-10 clustering (DAC)ACC: 0.5013 -> 0.5400Improved
increase sampling times K beyond 3-4 (ablation)SLF · MNIST/CIFAR-10accuracyHurt
use SLF on imbalanced MNIST subsets (ablation)DAC · imbalanced MNIST clusteringaccuracy: more than 5% pointImproved
use learnable adaptive robust loss (ARLF) instead of handcrafted large-margin softmaxbaseline loss · CIFAR-10 ResNet-8accuracy: 0.8866 -> 0.8646Hurt

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