Strong self-concordance and sampling
Aditi Laddha, Yin Tat Lee, Santosh S. Vempala
Abstract
Motivated by the Dikin walk, we develop aspects of an interior-point theory for sampling in high dimension. Specifically, we introduce a symmetric parameter and the notion of strong self-concordance. These properties imply that the corresponding Dikin walk mixes in Õ(nν) steps from a warm start in a convex body in R n using a strongly self-concordant barrier with symmetric self-concordance parameter ν. For many natural barriers, ν is roughly bounded by ν, the standard self-concordance parameter. We show that this property and strong self-concordance hold for the Lee-Sidford barrier. As a consequence, we obtain the first walk to mix in Õ(n 2 ) steps for an arbitrary polytope in R n . Strong self-concordance for other barriers leads to an interesting (and unexpected) connection -for the universal and entropic barriers, it is implied by the KLS conjecture.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 2a7cef40-858e-49ac-a751-88e3f58ad0f6Cited by top-tier papers12
- Efficient constrained sampling via the mirror-Langevin algorithmKwangjun Ahn, Sinho ChewiNeurIPS 2021 · 77 citations
- Exponential ergodicity of mirror-Langevin diffusionsSinho Chewi, Thibaut Le Gouic, Chen Lu, Tyler Maunu et al.NeurIPS 2020 · 62 citations
- Solving SDP Faster: A Robust IPM Framework and Efficient ImplementationBaihe Huang, Shunhua Jiang, Zhao Song, Runzhou Tao et al.FOCS 2022 · 17 citations
- Computing Approximate 𝓁p SensitivitiesSwati Padmanabhan, David P. Woodruff, Richard ZhangNeurIPS 2023 · 5 citations
- Computing Lewis Weights to High PrecisionMaryam Fazel, Yin Tat Lee, Swati Padmanabhan, Aaron SidfordSODA 2022 · 4 citations
Related papers
- Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin WalkYuzhou Gu, Nikki Lijing Kuang, Yian Ma, Zhao Song et al.NeurIPS 2024 · 2 citations
- Sampling from Structured Log-Concave Distributions via a Soft-Threshold Dikin WalkOren Mangoubi, Nisheeth K. VishnoiNeurIPS 2023 · 2 citations
- Faster Logconcave Sampling from a Cold Start in High DimensionYunbum Kook, Santosh S. VempalaFOCS 2025 · 11 citations
- No self-concordant barrier interior point method is strongly polynomialXavier Allamigeon, Stéphane Gaubert, Nicolas VandameSTOC 2022 · 8 citations
- In-and-Out: Algorithmic Diffusion for Sampling Convex BodiesYunbum Kook, Santosh S. Vempala, Matthew Shunshi ZhangNeurIPS 2024 · 25 citations
