Research map / Optimization / Nonconvex and smooth optimization
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise
Eduard Gorbunov, Marina Danilova, David Dobre, Pavel Dvurechensky, Alexander Gasnikov, Gauthier Gidel
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add gradient norm clipping to SGDA/SEG | WGAN-GP ResNet · CIFAR-10 | FID: 67.37 -> 19.65 | Improved |
| add coordinate clipping to SGDA | StyleGAN2 · FFHQ 128x128 | FID: 320 -> 72.68 | Improved |
| use coordinate-wise clipping in addition to norm clipping (ablation) | clipped-SGDA · StyleGAN2 FFHQ | FID | Improved |
Closest papers by meaning
- Clipped Gradient Methods for Nonsmooth Convex Optimization under Heavy-Tailed Noise: A Refined Analysis (ICLR 2026 · similarity 0.92)
- High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise (ICML 2024 · similarity 0.91)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.90)
- Generalized Smooth Stochastic Variational Inequalities: Almost Sure Convergence and Convergence Rates (NeurIPS 2026 · similarity 0.90)
- Second-order Optimization under Heavy-Tailed Noise: Hessian Clipping and Sample Complexity Limits (NeurIPS 2025 · similarity 0.90)
- Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise (NeurIPS 2026 · similarity 0.89)
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.
