Research map / Optimization / Nonconvex and smooth optimization
Accelerating Stochastic Composition Optimization
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 |
|---|---|---|---|
| Use ASC-PG instead of the prior SCGD rate result | Stochastic composition, smooth nonconvex · Stochastic composition, smooth nonconvex | average squared gradient norm convergence rate: O(k^{-2/7}) -> O(K^{-4/9}) | Helped |
| Use ASC-PG when the inner mapping is linear | ASC-PG · Stochastic composition with linear inner mapping | squared distance to optimal solution set convergence rate: O(k^{-4/5}) -> O(k^{-1}) | Helped |
| Use ASC-PG when the outer function is linear | ASC-PG · Stochastic composition with linear outer function | squared distance to optimal solution set convergence rate: O(k^{-4/5}) -> O(k^{-1}) | Helped |
| Use ASC-PG for Bellman equation solving with a linear inner mapping | On-policy reinforcement learning · Bellman equations | convergence rate: O(1/K) | Helped |
| Add the extrapolation-smoothing auxiliary update | ASC-PG · Stochastic composition optimization | convergence rate | Helped |
| Use a proximal step to support nonsmooth regularization | ASC-PG · Penalized stochastic composition | convergence rate | Helped |
Closest papers by meaning
- Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization (NeurIPS 2024 · similarity 0.89)
- Stability and Generalization of Stochastic Compositional Gradient Descent Algorithms (ICML 2024 · similarity 0.89)
- Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization (AAAI 2024 · similarity 0.88)
- A Near-Optimal Single-Loop Stochastic Algorithm for Convex Finite-Sum Coupled Compositional Optimization (ICML 2025 · similarity 0.86)
- Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity (ICML 2025 · similarity 0.86)
- Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling (ICML 2025 · similarity 0.86)
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.