English
Related papers

Related papers: Improved bounds on sample size for implicit matrix…

200 papers

Matrix trace estimation is ubiquitous in machine learning applications and has traditionally relied on Hutchinson's method, which requires $O(\log(1/\delta)/\epsilon^2)$ matrix-vector product queries to achieve a $(1 \pm…

Data Structures and Algorithms · Computer Science 2021-11-02 Shuli Jiang , Hai Pham , David P. Woodruff , Qiuyi , Zhang

We study the problem of estimating an unknown vector $\theta$ from an observation $X$ drawn according to the normal distribution with mean $\theta$ and identity covariance matrix under the knowledge that $\theta$ belongs to a known closed…

Statistics Theory · Mathematics 2017-03-03 Xi Chen , Adityanand Guntuboyina , Yuchen Zhang

We propose an adaptive importance sampling scheme for Gaussian approximations of intractable posteriors. Optimization-based approximations like variational inference can be too inaccurate while existing Monte Carlo methods can be too slow.…

Computation · Statistics 2025-02-04 Willem van den Boom , Andrea Cremaschi , Alexandre H. Thiery

Langevin Monte Carlo (LMC) and its stochastic gradient versions are powerful algorithms for sampling from complex high-dimensional distributions. To sample from a distribution with density $\pi(\theta)\propto \exp(-U(\theta)) $, LMC…

Computation · Statistics 2023-09-25 Sifan Liu

A classical result of Johnson and Lindenstrauss states that a set of $n$ high dimensional data points can be projected down to $O(\log n/\epsilon^2)$ dimensions such that the square of their pairwise distances is preserved up to a small…

Data Structures and Algorithms · Computer Science 2023-06-02 Aleksandros Sobczyk , Mathieu Luisier

Monte Carlo methods are used to approximate the means, $\mu$, of random variables $Y$, whose distributions are not known explicitly. The key idea is that the average of a random sample, $Y_1, ..., Y_n$, tends to $\mu$ as $n$ tends to…

Statistics Theory · Mathematics 2015-01-16 Fred J. Hickernell , Lan Jiang , Yuewei Liu , Art Owen

Many methods for machine learning rely on approximate inference from intractable probability distributions. Variational inference approximates such distributions by tractable models that can be subsequently used for approximate inference.…

Machine Learning · Computer Science 2020-10-08 Oleg Arenz , Mingjun Zhong , Gerhard Neumann

Exact approximations of Markov chain Monte Carlo (MCMC) algorithms are a general emerging class of sampling algorithms. One of the main ideas behind exact approximations consists of replacing intractable quantities required to run standard…

Computation · Statistics 2015-10-30 Christophe Andrieu , Matti Vihola

We show that the distance in total variation between $(\mathrm{Tr}\ U, \frac{1}{\sqrt{2}}\mathrm{Tr}\ U^2, \cdots, \frac{1}{\sqrt{m}}\mathrm{Tr}\ U^m)$ and a real Gaussian vector, where $U$ is a Haar distributed orthogonal or symplectic…

Probability · Mathematics 2021-03-08 Klara Courteaut , Kurt Johansson

We present new estimators of the mean of a real valued random variable, based on PAC-Bayesian iterative truncation. We analyze the non-asymptotic minimax properties of the deviations of estimators for distributions having either a bounded…

Statistics Theory · Mathematics 2009-09-30 Olivier Catoni

Hamiltonian Monte Carlo (HMC) is a widely deployed method to sample from high-dimensional distributions in Statistics and Machine learning. HMC is known to run very efficiently in practice and its popular second-order "leapfrog"…

Data Structures and Algorithms · Computer Science 2018-08-13 Oren Mangoubi , Nisheeth K. Vishnoi

We obtain non asymptotic concentration bounds for two kinds of stochastic approximations. We first consider the deviations between the expectation of a given function of the Euler scheme of some diffusion process at a fixed deterministic…

Probability · Mathematics 2012-12-12 Noufel Frikha , Stephane Menozzi

We present simple, user-friendly bounds for the expected operator norm of a random kernel matrix under general conditions on the kernel function $k(\cdot,\cdot)$. Our approach uses decoupling results for U-statistics and the non-commutative…

Machine Learning · Statistics 2025-11-07 Chiraag Kaushik , Justin Romberg , Vidya Muthukumar

Some recent work on confidence intervals for randomized quasi-Monte Carlo (RQMC) sampling found a surprising result: ordinary Student $t$ 95% confidence intervals based on a modest number of replicates were seen to be very effective and…

Numerical Analysis · Mathematics 2025-03-26 Zexin Pan , Art B. Owen

It is a standard criterium in statistics to define an optimal estimator the one with the minimum variance. Thus, the optimality is proved with inequality among variances of competing estimators. The inequalities, demonstrated here, disfavor…

Statistics Theory · Mathematics 2021-10-22 Gregorio Landi , Giovanni E. Landi

Random-effects meta-analyses have been widely applied in evidence synthesis for various types of medical studies. However, standard inference methods (e.g. restricted maximum likelihood estimation) usually underestimate statistical errors…

Methodology · Statistics 2019-05-13 Shonosuke Sugasawa , Hisashi Noma

In this paper we consider the trace regression model. Assume that we observe a small set of entries or linear combinations of entries of an unknown matrix $A_0$ corrupted by noise. We propose a new rank penalized estimator of $A_0$. For…

Statistics Theory · Mathematics 2011-09-14 Olga Klopp

Approximating integrals is a fundamental task in probability theory and statistical inference, and their applied fields of signal processing, and Bayesian learning, as soon as expectations over probability distributions must be computed…

Statistics Theory · Mathematics 2026-05-06 Solal Martin , Emilie Chouzenoux , Victor Elvira

We consider a method for approximate inference in hidden Markov models (HMMs). The method circumvents the need to evaluate conditional densities of observations given the hidden states. It may be considered an instance of Approximate…

Computation · Statistics 2012-06-25 James S. Martin , Ajay Jasra , Sumeetpal S. Singh , Nick Whiteley , Emma McCoy

While one-dimensional Markov processes are well understood, going to higher dimensions there are only a few analytically solved Ising-like models, in practice requiring to use relatively costly, uncontrollable and inaccurate Monte-Carlo…

Information Theory · Computer Science 2021-04-20 Jarek Duda