AI Paper Atlas

Research map / Optimization / Optimizers

Gradient Flow Sampler-based Distributionally Robust Optimization

Zusen Xu, Jia-Jie Zhu

ICML 2026 · Optimization › Optimizers · approach: Stochastic gradient MCMC · 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
add birth-death (Fisher-Rao) reaction to Wasserstein gradient flow sampler (ablation)WGF-DRO · MNIST LeNet-5 PGD-L2 (delta=0.075)test error (%): 21.57 -> 20.81Improved
add birth-death reaction to WGF-DRO (ablation)WGF-DRO · CIFAR-10 ResNet-18 PGD-L2 (delta=0.015)test error (%): 27.70 -> 26.73Improved
add birth-death reaction to WGF-DRO (ablation)WGF-DRO · CIFAR-10 ResNet-18 PGD-Linf (delta=0.015)test error (%): 35.02 -> 34.06Improved
add Langevin noise (SDE) to WRM's ODE inner step, i.e. entropy regularization (ablation)WRM · MNIST LeNet-5 PGD-L2 (delta=0.075)test error (%): 29.22 -> 21.57Improved
replace deterministic ODE with SDE in the inner sampler (ablation)WRM · CIFAR-10 ResNet-18 PGD-L2 (delta=0.015)test error (%): 71.24 -> 27.70Improved
use WRM instead of plain SAA trainingSAA · MNIST LeNet-5test error (%): 10.80 -> 11.66 (delta=0.05, L2)No clear effect
use WRM instead of plain SAA trainingSAA · CIFAR-10 ResNet-18 PGD-L2 (delta=0.015)test error (%): 78.32 -> 71.24Improved
use WFR-DRO instead of Dual Sinkhorn DRODual · MNIST LeNet-5 PGD-L2 (delta=0.075)test error (%): 24.20 -> 20.81Improved
use WFR-DRO instead of Dual Sinkhorn DRODual · CIFAR-10 ResNet-18 PGD-Linf (delta=0.015)test error (%): 39.74 -> 34.06Improved
use WFR-DRO instead of SAA on clean dataSAA · CIFAR-10 ResNet-18 (delta=0.00)test error (%): 6.35 -> 11.10Hurt
use WFR-DRO instead of SAA on clean dataSAA · MNIST LeNet-5 (delta=0.00)test error (%): 0.92 -> 0.92No clear effect
use Stein variational gradient flow sampler (SVG-DRO)GF-DRO · convex feature-extracted CIFAR-10robustnessHurt

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