paper-with-me

홈 › Papers

PAC-Bayes Iterated Logarithm Bounds for Martingale Mixtures

2015-06-22 · Akshay Balsubramani

We give tight concentration bounds for mixtures of martingales that are simultaneously uniform over (a) mixture distributions, in a PAC-Bayes sense; and (b) all finite times. These bounds are proved in terms of the martingale variance, extending classical Bernstein inequalities, and sharpening and simplifying prior work.

📄 PDF Abstract BibTeX arXiv:1506.06573

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sharp Finite-Time Iterated-Logarithm Martingale Concentration

2014-05-12 · Akshay Balsubramani

We give concentration bounds for martingales that are uniform over finite times and extend classical Hoeffding and Bernstein inequalities. We also demonstrate our concentration bounds to be optimal with a matching anti-c…

A unified recipe for deriving (time-uniform) PAC-Bayes bounds

2023-02-07 · Ben Chugg, Hongjian Wang, Aaditya Ramdas

We present a unified framework for deriving PAC-Bayesian generalization bounds. Unlike most previous literature on this topic, our bounds are anytime-valid (i.e., time-uniform), meaning that they hold at all stopping tim…

Generalization Boundsvalid

Concentration of Cumulative Reward in Markov Decision Processes

2024-11-27 · Borna Sayedana, Peter E. Caines, Aditya Mahajan

In this paper, we investigate the concentration properties of cumulative rewards in Markov Decision Processes (MDPs), focusing on both asymptotic and non-asymptotic settings. We introduce a unified approach to characteri…

Learning Unstable Continuous-Time Stochastic Linear Control Systems

2024-09-17 · Reza Sadeghi Hafshejani, Mohamad Kazem Shirani Fradonbeh

We study the problem of system identification for stochastic continuous-time dynamics, based on a single finite-length state trajectory. We present a method for estimating the possibly unstable open-loop matrix by employ…

Information on trajectories: martingales and random times

2026-08-20 · Akshay Balsubramani arxiv

Accounting for information flow on the path space of trajectories of a nonnegative martingale yields exact variational identities for it, even at arbitrary random times. This recovers the widely used classical concentrat…