paper-with-me

홈 › Papers

Dimension-free Information Concentration via Exp-Concavity

2018-02-26 · Ya-Ping Hsieh, Volkan Cevher

Information concentration of probability measures have important implications in learning theory. Recently, it is discovered that the information content of a log-concave distribution concentrates around their differential entropy, albeit with an unpleasant dependence on the ambient dimension. In this work, we prove that if the potentials of the log-concave distribution are exp-concave, which is a central notion for fast rates in online and statistical learning, then the concentration of information can be further improved to depend only on the exp-concavity parameter, and hence, it can be dimension independent. Central to our proof is a novel yet simple application of the variance Brascamp-Lieb inequality. In the context of learning theory, our concentration-of-information result immediately implies high-probability results to many of the previous bounds that only hold in expectation.

📄 PDF Abstract BibTeX arXiv:1802.09301

Code (0)

등록된 구현이 없습니다.

Tasks

Learning Theory

Similar Papers 제목 키워드 기반

Dimension-free Concentration Bounds on Hankel Matrices for Spectral Learning

2013-12-21 · François Denis, Mattias Gybels, Amaury Habrard

Learning probabilistic models over strings is an important issue for many applications. Spectral methods propose elegant solutions to the problem of inferring weighted automata from finite samples of variable-length stri…

Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo

2024-01-22 · Haoyang Zheng, Wei Deng, Christian Moya, Guang Lin

Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors. However, it still encounters scalability issues in high-dimensional…

Thompson Sampling

A Dimension-free Algorithm for Contextual Continuum-armed Bandits

2019-07-15 · Wenhao Li, Ningyuan Chen, L. Jeff Hong

In contextual continuum-armed bandits, the contexts $x$ and the arms $y$ are both continuous and drawn from high-dimensional spaces. The payoff function to learn $f(x,y)$ does not have a particular parametric form. The l…

Dimension-free uniform concentration bound for logistic regression

2024-05-28 · Shogo Nakakita

We provide a novel dimension-free uniform concentration bound for the empirical risk function of constrained logistic regression. Our bound yields a milder sufficient condition for a uniform law of large numbers than con…

regression

Universal Inference Meets Random Projections: A Scalable Test for Log-concavity

2021-11-17 · Robin Dunn, Aditya Gangrade, Larry Wasserman, Aaditya Ramdas

Shape constraints yield flexible middle grounds between fully nonparametric and fully parametric approaches to modeling distributions of data. The specific assumption of log-concavity is motivated by applications across …

valid