AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Noise Tolerance of Distributionally Robust Learning

Ramzi Dakhmouche, Ivan Lunati, Hossein Gorji

ICLR 2026 · Adversarial robustness and security › Certified and empirical robustness · approach: Theory of adversarial risk · 0 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 WBM (Wasserstein batch matching) loss instead of MSE under noisy dataconvolutional neural operator · Navier-Stokes and wave equation operator learning, noisy train/testtest MAEImproved
train with WBM instead of WDRL under 30% Cauchy-corrupted training dataNavier-Stokes operator learning · Navier-Stokes (Cauchy noise)test MAEImproved
use WBM instead of CVaR and Chi-Sq DRONavier-Stokes operator learning · Navier-Stokes (Gaussian noise)test MAEImproved
use WBM instead of MSE for TSMixer forecastingTSMixer · ETDataset electric load forecasting (noisy)test MAEImproved
use WBM instead of WDRL for training timeWDRL · Navier-Stokes operator learning (training time, no tuning)execution time (s): 3476.27 -> 2160.92Improved
WBM with multiplicative noiseWBM · Navier-Stokes (multiplicative noise)relative MAENo clear effect
WBM with strongly correlated noiseWBM · Navier-Stokes (correlated noise)relative errorHurt
WBM in low-noise regime vs MSEWBM · low-noise regimetest errorHurt
vary batch size for WBM (up to 80) (ablation)WBM · Navier-Stokes (noise level 1)relative test errorNo 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