Research map / Optimization / Nonconvex and smooth optimization
Adaptive Three Operator Splitting
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 Adaptive TOS Variant 2 with growing step sizes instead of fixed-step-size methods | Adaptive TOS · 12 optimization experiments | computational performance: best performing on 10 out of 12 experiments | Helped |
| Use Adaptive TOS Variant 2 with growing step sizes instead of fixed-step-size methods | Adaptive TOS · Low-regularization experiments | time to convergence: on 3 out of 6 the adaptive TOS is an order of magnitude faster | Helped |
| Use Adaptive TOS Variant 2 with growing step sizes instead of fixed-step-size methods | Adaptive TOS · High-regularization experiments | time to convergence: never more than a factor 2.6 | Helped |
| Allow the step size to grow (Variant 2) rather than only decrease or remain fixed (Variant 1) (ablation) | Adaptive TOS · Optimization benchmarks | computational performance | Helped |
| Apply adaptive step sizes to smooth terms with non-uniform rather than uniform curvature | Adaptive TOS · Optimization benchmarks | computational performance | Helped |
| Use Adaptive TOS Variant 2 rather than other compared methods | Adaptive TOS · Experiments E and H | computational performance | No clear effect |
Closest papers by meaning
- Three Operator Splitting with Subgradients, Stochastic Gradients, and Adaptive Learning Rates (NeurIPS 2021 · similarity 0.91)
- Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization (NeurIPS 2024 · similarity 0.86)
- On the Almost Sure Convergence of the Stochastic Three Points Algorithm (ICLR 2025 · similarity 0.86)
- Fundamental Benefit of Alternating Updates in Minimax Optimization (ICML 2024 · similarity 0.85)
- Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction (NeurIPS 2024 · similarity 0.85)
- Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity (ICLR 2025 · similarity 0.85)
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.