Research map / Optimization / Nonconvex and smooth optimization
Stability and Convergence of Stochastic Gradient Clipping: Beyond Lipschitz Continuity and Smoothness
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 clipping to SGD and stochastic heavy ball | SGD and SHB · Phase retrieval | stability across initial step sizes | Helped |
| Add gradient clipping to SGD and stochastic heavy ball | SGD and SHB · Absolute linear regression | final accuracy | Mixed |
| Use gradient clipping instead of no clipping | SGD and SHB · CIFAR10 with ResNet-18 | test accuracy | Helped |
| Use Adam instead of the clipped and unclipped SGD-family methods | CIFAR10 with ResNet-18 · CIFAR10 | stepsize sensitivity | Hurt |
Closest papers by meaning
- Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions (NeurIPS 2025 · similarity 0.94)
- Clipped SGD Algorithms for Performative Prediction: Tight Bounds for Stochastic Bias and Remedies (ICML 2025 · similarity 0.90)
- Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity (ICLR 2025 · similarity 0.90)
- Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis (NeurIPS 2025 · similarity 0.90)
- High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise (ICML 2024 · similarity 0.90)
- To Clip or not to Clip: the Dynamics of SGD with Gradient Clipping in High-Dimensions (ICLR 2025 · similarity 0.90)
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.