AI Paper Atlas

Research map / Optimization / Optimizers

Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling

Yu-Guan Hsieh, Franck Iutzeler, Jérôme Malick, Panayotis Mertikopoulos

NeurIPS 2020 · Optimization › Optimizers · approach: SGD momentum and step-size schedules

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
use a more aggressive exploration stepsize than the update stepsize (double stepsize) in stochastic extragradient (ablation)stochastic extragradient (DSEG) · stochastic bilinear gameconvergence of last iterateImproved
use a more aggressive exploration stepsize than the update stepsize (double stepsize) in stochastic extragradient (ablation)stochastic extragradient (DSEG) · non convex-concave linear quadratic Gaussian GANconvergence of last iterateImproved
use an aggressive exploration stepsize in addition to the update stepsize (ablation)stochastic extragradient (DSEG) · strongly convex-concave gameconvergence speedNo clear effect
use DSEG instead of anchored gradient descentstochastic bilinear saddle-point example · stochastic bilinear gameconvergence speedImproved
use stochastic Hamiltonian gradient descent instead of DSEGstochastic bilinear saddle-point example · stochastic bilinear gameearly convergence speedMixed
use vanilla stochastic extragradient with any stepsize sequencestochastic extragradient · bilinear min-max with noisy feedbacklast-iterate convergenceHurt

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