Research map / Optimization / Optimizers
On Perturbed Proximal Gradient Algorithms
Yves F. Atchadé, Gersende Fort, Eric Moulines
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 |
|---|---|---|---|
| use a step size decreasing as 1/sqrt(n) rather than 1/n with a fixed Monte Carlo batch size (ablation) | Monte Carlo proximal gradient with fixed batch size · Random-effect logistic regression (N=500, p=1000) | relative error convergence: gamma_n = 0.01/sqrt(n) (Algo 1) vs gamma_n = 0.5/n (Algo 2), m_n = 275 | Improved |
| use a fixed step size with an increasing Monte Carlo batch size (ablation) | Monte Carlo proximal gradient with increasing batch size · Random-effect logistic regression (N=500, p=1000) | relative error convergence: fixed gamma = 0.005 or 0.001 with m_n = 200+n (Algo 3, 4) vs 0.05/sqrt(n) with m_n = 270+ceil(sqrt(n)) (Algo 5) | Improved |
| increasing batch size with fixed step instead of fixed batch size with decreasing step (ablation) | stochastic proximal gradient for Potts model structure estimation · Potts model, p in {50,100,200}, M=20, N=250 | relative error vs computing time: Solver 1 (m_n=500) vs Solver 2 (m_n=500+n^1.2) | No clear effect |
Closest papers by meaning
- Adaptive Proximal Gradient Methods for Structured Neural Networks (NeurIPS 2021 · similarity 0.89)
- Stochastic Proximal Methods for Non-Smooth Non-Convex Constrained Sparse Optimization (JMLR 2021 · similarity 0.89)
- Convergence Rate of the Last Iterate of Stochastic Proximal Algorithms (ICML 2026 · similarity 0.88)
- Hybrid Stochastic-Deterministic Minibatch Proximal Gradient: Less-Than-Single-Pass Optimization with Nearly Optimal Generalization (ICML 2020 · similarity 0.88)
- A Hybrid Stochastic-Deterministic Minibatch Proximal Gradient Method for Efficient Optimization and Generalization (TPAMI 2021 · similarity 0.88)
- Faster Sampling via Stochastic Gradient Proximal Sampler (ICML 2024 · similarity 0.87)
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.
