The entropic barrier: a simple and optimal universal self-concordant barrier
S\'ebastien Bubeck, Ronen Eldan

TL;DR
This paper introduces an explicit universal self-concordant barrier for convex bodies, based on the Cramér transform of the uniform measure, achieving optimal parameters and improving prior results.
Contribution
It provides the first explicit construction of a universal barrier with optimal self-concordance parameter for convex bodies, utilizing geometric and exponential family duality.
Findings
Cramér transform of uniform measure is an (1+o(1)) n-self-concordant barrier
Improves a seminal result of Nesterov and Nemirovski
Provides explicit construction with optimal parameters
Abstract
We prove that the Cram\'er transform of the uniform measure on a convex body in is a -self-concordant barrier, improving a seminal result of Nesterov and Nemirovski. This gives the first explicit construction of a universal barrier for convex bodies with optimal self-concordance parameter. The proof is based on basic geometry of log-concave distributions, and elementary duality in exponential families.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Bandit Algorithms Research · Reinforcement Learning in Robotics · Markov Chains and Monte Carlo Methods
