AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Learning from A Single Markovian Trajectory: Optimality and Variance Reduction

Zhenyu Sun, Ermin Wei

NeurIPS 2025 · Optimization › Nonconvex and smooth optimization · approach: Variance-reduced policy gradient · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies stochastic non-convex optimization when samples come from a single Markovian trajectory and proposes a variance-reduced method claimed to be optimal.

Problem

Stochastic non-convex optimization where samples are drawn from a Markov chain along one trajectory, with no prior knowledge or control of the chain, relevant to asynchronous distributed learning and reinforcement learning.

Approach

Treats the worst case where multiple trajectories or i.i.d. sampling are unavailable and the Markov chain cannot be controlled; the abstract indicates the approach achieves optimality and reduces variance for learning from a single Markovian trajectory.

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy