Research map / Learning theory and algorithms / Sample complexity
The Adaptive Complexity of Minimizing Relative Fisher Information
Huanjian Zhou, Masashi Sugiyama
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.
Initiates the study of adaptive complexity (number of sequential rounds) of non-log-concave sampling by framing it as minimizing relative Fisher information.
Problem
Non-log-concave sampling from unnormalized densities is central to ML and statistics, but sampling algorithms need many sequential rounds, and the adaptive complexity of this problem has not been studied.
Approach
Studies the adaptive complexity of non-log-concave sampling within the framework of minimizing relative Fisher information, aiming to reduce the number of sequential rounds rather than total gradient evaluations.
Closest papers by meaning
- Parallel Simulation for Log-concave Sampling and Score-based Diffusion Models (ICML 2025 · similarity 0.88)
- Sample-Adaptivity Tradeoff in On-Demand Sampling (NeurIPS 2025 · similarity 0.86)
- Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers (ICLR 2024 · similarity 0.86)
- Improved Sample Complexity for Private Nonsmooth Nonconvex Optimization (ICML 2025 · similarity 0.86)
- Chain of Log-Concave Markov Chains (ICLR 2024 · similarity 0.85)
- The Sample Complexity of Gradient Descent in Stochastic Convex Optimization (NeurIPS 2024 · 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.
