Research map / Bandits and online learning / Online convex optimization and games
Stochastic Zeroth-Order Optimization under Nonstationarity and Nonconvexity
Abhishek Roy, Krishnakumar Balasubramanian, Saeed Ghadimi, Prasant Mohapatra
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 zeroth-order two-point gradient estimates (Algorithm 1) instead of exact stochastic gradients | first-order nonstationary regret algorithm · Synthetic nonstationary nonconvex problem, two-point setting, T=2000, W_T=sqrt(T) | cumulative first-order regret | No clear effect |
| use zeroth-order one-point gradient estimates instead of exact stochastic gradients | first-order nonstationary regret algorithm · Synthetic nonstationary nonconvex problem, one-point setting, T=2000 | cumulative first-order regret | No clear effect |
| use zeroth-order cubic-regularized Newton (Algorithm 3) instead of one with Hessian access (Algorithm 2) | higher-order cubic Newton algorithm · Synthetic nonstationary nonconvex problem, T=1000, W_T=sqrt(T) | cumulative second-order regret | No clear effect |
Closest papers by meaning
- Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity (NeurIPS 2024 · similarity 0.89)
- Exploiting Higher Order Smoothness in Derivative-free Optimization and Continuous Bandits (NeurIPS 2020 · similarity 0.88)
- Guided Zeroth-Order Methods for Stochastic Non-convex Problems with Decision-Dependent Distributions (ICML 2025 · similarity 0.88)
- Stochastic Zeroth-Order Optimization Under Heavy-Tailed Noise (NeurIPS 2026 · similarity 0.88)
- Non-stationary Bandit Convex Optimization: A Comprehensive Study (NeurIPS 2025 · similarity 0.87)
- Zeroth-Order Methods for Nonconvex Stochastic Problems with Decision-Dependent Distributions (AAAI 2025 · 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.
