English
Related papers

Related papers: Instance-optimal estimation of L2-norm

200 papers

We prove that the ordinary least-squares (OLS) estimator attains nearly minimax optimal performance for the identification of linear dynamical systems from a single observed trajectory. Our upper bound relies on a generalization of…

Machine Learning · Computer Science 2018-05-25 Max Simchowitz , Horia Mania , Stephen Tu , Michael I. Jordan , Benjamin Recht

We give a general unified method that can be used for $L_1$ {\em closeness testing} of a wide range of univariate structured distribution families. More specifically, we design a sample optimal and computationally efficient algorithm for…

Data Structures and Algorithms · Computer Science 2015-08-25 Ilias Diakonikolas , Daniel M. Kane , Vladimir Nikishkin

We study the problem of learning nonparametric distributions in a finite mixture, and establish tight bounds on the sample complexity for learning the component distributions in such models. Namely, we are given i.i.d. samples from a pdf…

Machine Learning · Computer Science 2023-07-06 Bryon Aragam , Wai Ming Tai

Fitting probabilistic models to data is often difficult, due to the general intractability of the partition function and its derivatives. Here we propose a new parameter estimation technique that does not require computing an intractable…

Machine Learning · Computer Science 2015-03-13 Jascha Sohl-Dickstein , Peter Battaglino , Michael R. DeWeese

In this paper, we develop a general machinery for finding explicit uniform probability and moment bounds on sub-additive positive functionals of random processes. Using the developed general technique, we derive uniform bounds on the…

Probability · Mathematics 2012-02-09 Alexander Goldenshluger , Oleg Lepski

Motivated by applications in deep learning, where the global Lipschitz continuity condition is often not satisfied, we examine the problem of sampling from distributions with super-linearly growing log-gradients. We propose a novel tamed…

Statistics Theory · Mathematics 2025-06-06 Iosif Lytras , Sotirios Sabanis , Ying Zhang

Suppose that $X_1,X_2,\ldots$ are a stream of independent, identically distributed Poisson random variables with mean $\mu$. This work presents a new estimate $\mu_k$ for $\mu$ with the property that the distribution of the relative error…

Computation · Statistics 2016-06-01 Mark Huber

This paper considers the secure state estimation problem for noisy systems in the presence of sparse sensor integrity attacks. We show a fundamental limitation: that is, 2r-detectability is necessary for achieving bounded estimation errors,…

Optimization and Control · Mathematics 2018-03-20 Yorie Nakahira , Yilin Mo

Given a set of 2-dimensional (2-D) scattering points, which are usually obtained from the edge detection process, the aim of ellipse fitting is to construct an elliptic equation that best fits the collected observations. However, some of…

Image and Video Processing · Electrical Eng. & Systems 2018-06-04 Hao Wang , Chi-Sing Leung , Hing Cheung So , Junli Liang , Ruibin Feng , Zifa Han

In the problem of online unweighted interval selection, the objective is to maximize the number of non-conflicting intervals accepted by the algorithm. In the conventional online model of irrevocable decisions, there is an Omega(n) lower…

Data Structures and Algorithms · Computer Science 2025-06-03 Allan Borodin , Christodoulos Karavasilis

We introduce a principled learning to optimize (L2O) framework for solving fixed-point problems involving general nonexpansive mappings. Our idea is to deliberately inject summable perturbations into a standard Krasnosel'skii-Mann iteration…

Systems and Control · Electrical Eng. & Systems 2026-01-13 Andrea Martin , Giuseppe Belgioioso

The Neyman-Pearson (NP) paradigm in binary classification seeks classifiers that achieve a minimal type II error while enforcing the prioritized type I error controlled under some user-specified level $\alpha$. This paradigm serves…

Methodology · Statistics 2020-01-30 Xin Tong , Lucy Xia , Jiacheng Wang , Yang Feng

Learning rates for least-squares regression are typically expressed in terms of $L_2$-norms. In this paper we extend these rates to norms stronger than the $L_2$-norm without requiring the regression function to be contained in the…

Machine Learning · Statistics 2020-10-27 Simon Fischer , Ingo Steinwart

In this article, we propose a novel logistic quasi-maximum likelihood estimation (LQMLE) for general parametric time series models. Compared to the classical Gaussian QMLE and existing robust estimations, it enjoys many distinctive…

Methodology · Statistics 2025-03-12 Zihan Wang , Xinghao Qiao , Dong Li , Howell Tong

We consider the algorithm by Ferson et al. (Reliable computing 11(3), p. 207-233, 2005) designed for solving the NP-hard problem of computing the maximal sample variance over interval data, motivated by robust statistics (in fact, the…

Optimization and Control · Mathematics 2022-07-28 Miroslav Rada , Michal Černý , Ondřej Sokol

Minimization of the $L_\infty$ norm, which can be viewed as approximately solving the non-convex least median estimation problem, is a powerful method for outlier removal and hence robust regression. However, current techniques for solving…

Computer Vision and Pattern Recognition · Computer Science 2013-04-05 Fumin Shen , Chunhua Shen , Rhys Hill , Anton van den Hengel , Zhenmin Tang

A new parameterization and algorithm are proposed for seeking the primary relative maximum of the likelihood function in the three-parameter lognormal distribution. The parameterization yields the dimension reduction of the three-parameter…

Statistics Theory · Mathematics 2013-11-18 Yoshio Komori , Hideo Hirose

Let $\mathbf{X} = (X_i)_{1\leq i \leq n}$ be an i.i.d. sample of square-integrable variables in $\mathbb{R}^d$, \GB{with common expectation $\mu$ and covariance matrix $\Sigma$, both unknown.} We consider the problem of testing if $\mu$ is…

Machine Learning · Computer Science 2021-10-11 Gilles Blanchard , Jean-Baptiste Fermanian

We analyze a recently proposed class of algorithms for the problem of sampling from probability distributions $\mu^\ast$ in $\mathbb{R}^d$ with a Lebesgue density of the form $\mu^\ast(x) \propto \exp(-f(Kx)-g(x))$, where $K$ is a linear…

Optimization and Control · Mathematics 2024-11-06 Martin Burger , Matthias J. Ehrhardt , Lorenz Kuger , Lukas Weigand

We prove a strong concentration result about the natural collision estimator, which counts the number of collisions that occur within an iid sample. This estimator is at the heart of algorithms used for uniformity testing and entropy…

Information Theory · Computer Science 2020-06-26 Maciej Skorski
‹ Prev 1 8 9 10 Next ›