AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Thomas Pethick, Wanyun Xie, Volkan Cevher

NeurIPS 2023 · Optimization › Nonconvex and smooth optimization · approach: Gradient descent ascent for minimax · 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 Lookahead-style linear interpolation on top of AdamAdam GAN training · CIFAR10 image generationstability (divergence)Improved
use extrapolation methods (EG, RAPP) instead of the baseline despite fewer effective iterations at equal gradient computationsGAN training · CIFAR10 image generationFID / ISCImproved
use RAPP instead of EG (more inner extrapolation steps, fewer updates)GAN training · CIFAR10 image generationFID / ISCImproved
use classical extragradient (simultaneous or alternating) under hinge lossGAN training · CIFAR10 image generationsample qualityHurt
use EG+ instead of AdamGAN training · CIFAR10 image generationstability and FID: FID 16.88, ISC 8.0Mixed
set Lookahead interpolation constant to 0.5Lookahead · theory, comonotone problemsconvergence guarantee: lambda = 0.5Improved
use many inner iterations tau in Lookahead with GDA/EGLookahead · theory, comonotone problemsconvergenceHurt

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