English
Related papers

Related papers: Analysis of radix selection on Markov sources

200 papers

Let $A$ be an isotropic, sub-gaussian $m \times n$ matrix. We prove that the process $Z_x := \|Ax\|_2 - \sqrt m \|x\|_2$ has sub-gaussian increments. Using this, we show that for any bounded set $T \subseteq \mathbb{R}^n$, the deviation of…

Probability · Mathematics 2016-06-08 Christopher Liaw , Abbas Mehrabian , Yaniv Plan , Roman Vershynin

Given a reference computer, Kolmogorov complexity is a well defined function on all binary strings. In the standard approach, however, only the asymptotic properties of such functions are considered because they do not depend on the…

Machine Learning · Computer Science 2007-05-23 Andrei N. Soklakov

The convergence, convergence rate and expected hitting time play fundamental roles in the analysis of randomised search heuristics. This paper presents a unified Markov chain approach to studying them. Using the approach, the sufficient and…

Optimization and Control · Mathematics 2013-12-10 Jun He , Feidun He , Xin Yao

Matrices with low-rank structure are ubiquitous in scientific computing. Choosing an appropriate rank is a key step in many computational algorithms that exploit low-rank structure. However, estimating the rank has been done largely in an…

Numerical Analysis · Mathematics 2024-01-08 Maike Meier , Yuji Nakatsukasa

The master equation and, more generally, Markov processes are routinely used as models for stochastic processes. They are often justified on the basis of randomization and coarse-graining assumptions. Here instead, we derive n-th order…

Statistical Mechanics · Physics 2012-09-27 Julian Lee , Steve Pressé

We consider a reinforcement learning setting in which the deployment environment is different from the training environment. Applying a robust Markov decision processes formulation, we extend the distributionally robust $Q$-learning…

Machine Learning · Computer Science 2024-08-02 Shengbo Wang , Nian Si , Jose Blanchet , Zhengyuan Zhou

Determining the most appropriate features for machine learning predictive models is challenging regarding performance and feature acquisition costs. In particular, global feature choice is limited given that some features will only benefit…

Machine Learning · Computer Science 2026-03-17 Gabriel Bernardino , Anders Jonsson , Patrick Clarysse , Nicolas Duchateau

Herein, we analyze an efficient branching particle method for asymptotic solutions to a class of continuous-discrete filtering problems. Suppose that $t\to X_t$ is a Markov process and we wish to calculate the measure-valued process…

Probability · Mathematics 2007-05-23 Michael A. Kouritzin , Wei Sun

The present paper gives a statistical adventure towards exploring the average case complexity behavior of computer algorithms. Rather than following the traditional count based analytical (pen and paper) approach, we instead talk in terms…

Data Structures and Algorithms · Computer Science 2013-12-18 Niraj Kumar Singh , Soubhik Chakraborty , Dheeresh Kumar Mallick

It is becoming increasingly apparent that probabilistic approaches can overcome conservatism and computational complexity of the classical worst-case deterministic framework and may lead to designs that are actually safer. In this paper we…

Applications · Statistics 2008-11-01 Xinjia Chen , Kemin Zhou , Jorge L. Aravena

We consider in this paper the problem of noisy 1-bit matrix completion under a general non-uniform sampling distribution using the max-norm as a convex relaxation for the rank. A max-norm constrained maximum likelihood estimate is…

Machine Learning · Statistics 2013-09-25 T. Tony Cai , Wen-Xin Zhou

The complexities of self-dual normal bases, which are candidates for the lowest complexity basis of some defined extensions, are determined with the help of the number of all but the simple points in well chosen minimal Besicovitch…

Combinatorics · Mathematics 2017-08-02 Stéphane Blondeau da Silva

In this paper, we propose practical normalized stochastic first-order methods with Polyak momentum, multi-extrapolated momentum, and recursive momentum for solving unconstrained optimization problems. These methods employ dynamically…

Optimization and Control · Mathematics 2026-02-12 Chuan He , Zhaosong Lu , Defeng Sun , Zhanwang Deng

As the issue of robustness in AI systems becomes vital, statistical learning techniques that are reliable even in presence of partly contaminated data have to be developed. Preference data, in the form of (complete) rankings in the simplest…

Machine Learning · Computer Science 2023-03-24 Morgane Goibert , Clément Calauzènes , Ekhine Irurozki , Stéphan Clémençon

We introduce a general framework for analyzing learning algorithms based on the notion of self-regularization, which captures implicit complexity control without requiring explicit regularization. This is motivated by previous observations…

Machine Learning · Statistics 2026-03-19 Max Schölpple , Liu Fanghui , Ingo Steinwart

Limit distributions for the greatest convex minorant and its derivative are considered for a general class of stochastic processes including partial sum processes and empirical processes, for independent, weakly dependent and long range…

Statistics Theory · Mathematics 2016-08-16 D. Anevski , O. Hössjer

A common assumption in machine learning is that samples are independently and identically distributed (i.i.d). However, the contributions of different samples are not identical in training. Some samples are difficult to learn and some…

Machine Learning · Computer Science 2021-11-23 Ou Wu , Weiyao Zhu , Yingjun Deng , Haixiang Zhang , Qinghu Hou

We construct and study branching Markov processes on the space of finite configurations of the state space of a given standard process, controlled by a branching kernel and a killing one. In particular, we may start with a superprocess,…

Probability · Mathematics 2015-08-03 Lucian Beznea , Oana Lupascu

Order-preserving couplings are elegant tools for obtaining robust estimates of the time-dependent and stationary distributions of Markov processes that are too complex to be analyzed exactly. The starting point of this paper is to study…

Probability · Mathematics 2009-06-02 Lasse Leskelä

We consider the problem of learning Bayesian network classifiers that maximize the marginover a set of classification variables. We find that this problem is harder for Bayesian networks than for undirected graphical models like maximum…

Machine Learning · Computer Science 2012-07-09 Yuhong Guo , Dana Wilkinson , Dale Schuurmans