Strong Self-Concordance and Sampling
Not on the map. Why?
Abstract (arXiv)
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 tildeO(nbarnu) steps from a warm start in a convex body in ℝn using a strongly self-concordant barrier with symmetric self-concordance parameter barnu. For many natural barriers, barnu is roughly bounded by nu, 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 tildeO(n2) steps for an arbitrary polytope in ℝn. 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.
Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Nov 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 4; 2024: 2; 2025: 1; 2026: 2.
11 papers.
- 2021The Mirror Langevin Algorithm Converges with Vanishing Biascited by 37
- 2023When does Metropolized Hamiltonian Monte Carlo provably outperform Metropolis-adjusted Langevin algorithm?cited by 12
- 2023Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithmcited by 11
- 2022Condition-number-independent convergence rate of Riemannian Hamiltonian Monte Carlo with numerical integratorscited by 10
- 2023Sampling with Barriers: Faster Mixing via Lewis Weightscited by 7
- 2025Tukey Depth Mechanisms for Practical Private Mean Estimationcited by 2
- 2024Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solverscited by 1
- 2024PolytopeWalk: Sparse MCMC Sampling over Polytopescited by 1
- 2026Beyond the d2.5-mixing bound for Dikin walks on polytopescited by 1
- 2023Computing Approximate ℓp Sensitivitiescited by 0
- 2026On two proofs of d2 mixing of weighted Dikin walkscited by 0
- 2026On two proofs of d2 mixing of weighted Dikin walks28 Aug 2026
- 2026Beyond the d2.5-mixing bound for Dikin walks on polytopes15 Jul 2026
- 2025Tukey Depth Mechanisms for Practical Private Mean Estimation25 Feb 2025
- 2024PolytopeWalk: Sparse MCMC Sampling over Polytopes9 Dec 2024
- 2024Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers6 Sep 2024
- 2023Fast sampling from constrained spaces using the Metropolis-adjusted Mirror Langevin algorithm14 Dec 2023
- 2023Computing Approximate ℓp Sensitivities7 Nov 2023
- 2023When does Metropolized Hamiltonian Monte Carlo provably outperform Metropolis-adjusted Langevin algorithm?10 Apr 2023
- 2023Sampling with Barriers: Faster Mixing via Lewis Weights1 Mar 2023
- 2022Condition-number-independent convergence rate of Riemannian Hamiltonian Monte Carlo with numerical integrators13 Oct 2022
- 2021The Mirror Langevin Algorithm Converges with Vanishing Bias24 Sep 2021