中文
相关论文

相关论文: Time-uniform Chernoff bounds via nonnegative super…

200 篇论文

We prove a Chernoff-type bound for sums of matrix-valued random variables sampled via a random walk on an expander, confirming a conjecture due to Wigderson and Xiao. Our proof is based on a new multi-matrix extension of the Golden-Thompson…

概率论 · 数学 2018-04-18 Ankit Garg , Yin Tat Lee , Zhao Song , Nikhil Srivastava

We develop a new framework for deriving time-uniform concentration bounds for the output of stochastic sequential algorithms satisfying certain recursive inequalities akin to those defining the almost-supermartingale processes introduced by…

统计理论 · 数学 2025-11-25 Tuan Pham , Alessandro Rinaldo , Purnamrita Sarkar

A confidence sequence is a sequence of confidence intervals that is uniformly valid over an unbounded time horizon. Our work develops confidence sequences whose widths go to zero, with nonasymptotic coverage guarantees under nonparametric…

统计理论 · 数学 2022-08-09 Steven R. Howard , Aaditya Ramdas , Jon McAuliffe , Jasjeet Sekhon

This paper derives confidence intervals (CI) and time-uniform confidence sequences (CS) for the classical problem of estimating an unknown mean from bounded observations. We present a general approach for deriving concentration bounds, that…

统计理论 · 数学 2022-08-29 Ian Waudby-Smith , Aaditya Ramdas

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-concentration…

概率论 · 数学 2015-12-03 Akshay Balsubramani

We establish Chernoff-type bounds for the largest eigenvalue of sums of Hermitian random matrices generated by a time-inhomogeneous Markov chain. Our primary regime assumes a compact state space and contractivity of each Markov kernel in…

概率论 · 数学 2026-05-26 Luca Zanetti

We consider the stochastic integrals of multivariate point processes and study their concentration phenomena. In particular, we obtain a Bernstein type of concentration inequality through Dol\'eans-Dade exponential formula and a uniform…

概率论 · 数学 2017-03-24 Hanchao Wang , Zhengyan Lin , Zhonggen Su

The martingale method is used to establish concentration inequalities for a class of dependent random sequences on a countable state space, with the constants in the inequalities expressed in terms of certain mixing coefficients. Along the…

概率论 · 数学 2009-01-22 Leonid , Kontorovich , Kavita Ramanan

This paper presents new probability inequalities for sums of independent, random, self-adjoint matrices. These results place simple and easily verifiable hypotheses on the summands, and they deliver strong conclusions about the…

概率论 · 数学 2014-04-29 Joel A. Tropp

We prove a Chernoff-type bound for sums of matrix-valued random variables sampled via a regular (aperiodic and irreducible) finite Markov chain. Specially, consider a random walk on a regular Markov chain and a Hermitian matrix-valued…

机器学习 · 统计学 2020-10-30 Jiezhong Qiu , Chi Wang , Ben Liao , Richard Peng , Jie Tang

We present new scalar and matrix Chernoff-style concentration bounds for a broad class of probability distributions over the binary hypercube $\{0,1\}^n$. Motivated by recent tools developed for the study of mixing times of Markov chains on…

离散数学 · 计算机科学 2022-01-07 Tali Kaufman , Rasmus Kyng , Federico Soldá

We consider estimating the shared mean of a sequence of heavy-tailed random variables taking values in a Banach space. In particular, we revisit and extend a simple truncation-based mean estimator first proposed by Catoni and Giulini. While…

统计理论 · 数学 2025-03-25 Justin Whitehouse , Ben Chugg , Diego Martinez-Taboada , Aaditya Ramdas

The Chernoff bound is an important inequality relation in probability theory. The original version of the Chernoff bound is to give an exponential decreasing bound on the tail distribution of sums of independent random variables. Recent…

概率论 · 数学 2021-05-18 Shih Yu Chang

This paper gives new concentration inequalities for the spectral norm of a wide class of matrix martingales in continuous time. These results extend previously established Freedman and Bernstein inequalities for series of random matrices to…

概率论 · 数学 2016-10-28 Emmanuel Bacry , Stéphane Gaïffas , Jean-François Muzy

We derive a Fuk-Nagaev inequality for the maxima of norms of martingale sequences in smooth Banach spaces which allow for a finite number of higher conditional moments. The bound is obtained by combining an optimization approach for a…

概率论 · 数学 2025-12-16 Mattes Mollenhauer , Christian Fiedler

We revisit the method of mixture technique, also known as the Laplace method, to study the concentration phenomenon in generic exponential families. Combining the properties of Bregman divergence associated with log-partition function of…

机器学习 · 计算机科学 2023-07-14 Sayak Ray Chowdhury , Patrick Saux , Odalric-Ambrym Maillard , Aditya Gopalan

As an alternative to the well-known methods of "chaining" and "bracketing" that have been developed in the study of random fields, a new method, which is based on a stochastic maximal inequality derived by using the Taylor expansion, is…

概率论 · 数学 2020-08-03 Yoichi Nishiyama

In this paper, we study moment and concentration inequalities for the spectral norm of sums of dependent random matrices. We establish novel Rosenthal-Burkholder inequalities for discrete-time matrix local martingales,…

概率论 · 数学 2025-11-13 Yang Peng , Yuchen Xin , Zhihua Zhang

In this work, Bernstein's concentration inequalities for squared integrable matrix-valued discrete-time martingales are obtained. Based on Lieb's theory and Bernstein's condition, a suitable supermartingale can be constructed. Our proof is…

概率论 · 数学 2021-03-26 Zijie Tian

Exponential inequalities are main tools in machine learning theory. To prove exponential inequalities for non i.i.d random variables allows to extend many learning techniques to these variables. Indeed, much work has been done both on…

机器学习 · 统计学 2020-08-03 Pierre Alquier , Paul Doukhan , Xiequan Fan
‹ 上一页 1 2 3 10 下一页 ›