Research map / Learning theory and algorithms / Sample complexity
Tight High Probability Bounds for Linear Stochastic Approximation with Fixed Stepsize
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 |
|---|---|---|---|
| Require almost-sure contraction of each update matrix | Fixed-step LSA · General linear stochastic approximation | high-probability tail dependence on δ | Helped |
| Use only the main assumptions, without almost-sure contraction of each update matrix | Fixed-step LSA · General linear stochastic approximation | high-probability tail dependence on δ | Mixed |
| Allow nonsymmetric random update matrices while requiring their mean to be Hurwitz | Fixed-step LSA · General linear stochastic approximation | applicability of the high-probability analysis | Helped |
Closest papers by meaning
- A General-Purpose Theorem for High-Probability Bounds of Stochastic Approximation with Polyak Averaging (NeurIPS 2025 · similarity 0.89)
- How Accurately Can a Gaussian Approximate Stochastic Approximation Iterates? (NeurIPS 2026 · similarity 0.88)
- Statistical inference for Linear Stochastic Approximation with Markovian Noise (NeurIPS 2025 · similarity 0.87)
- High-probability complexity bounds for stochastic non-convex minimax optimization (NeurIPS 2024 · similarity 0.86)
- Effectiveness of Constant Stepsize in Markovian LSA and Statistical Inference (AAAI 2024 · similarity 0.86)
- Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy (NeurIPS 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.