English
Related papers

Related papers: Near-Optimal Sample Complexity Bounds for Maximum …

200 papers

Suppose that $\m{U} = (U_1, \ldots , U_d) $ has a Uniform$([0,1]^d)$ distribution, that $\m{Y} = (Y_1 , \ldots , Y_d) $ has the distribution $G$ on $\RR_+^d$, and let $\m{X} = (X_1 , \ldots , X_d) = (U_1 Y_1 , \ldots , U_d Y_d )$. The…

Statistics Theory · Mathematics 2010-05-11 Marios G. Pavlides , Jon A. Wellner

Training an energy-based model (EBM) with maximum likelihood is challenging due to the intractable normalisation constant. Traditional methods rely on expensive Markov chain Monte Carlo (MCMC) sampling to estimate the gradient of logartihm…

Machine Learning · Computer Science 2025-03-11 Hugo Senetaire , Paul Jeha , Pierre-Alexandre Mattei , Jes Frellsen

Linear structural equation models postulate noisy linear relationships between variables of interest. Each model corresponds to a path diagram, which is a mixed graph with directed edges that encode the domains of the linear functions and…

Statistics Theory · Mathematics 2018-05-16 Mathias Drton , Christopher Fox , Andreas Käufl , Guillaume Pouliot

We provide a new convergence analysis of stochastic gradient Langevin dynamics (SGLD) for sampling from a class of distributions that can be non-log-concave. At the core of our approach is a novel conductance analysis of SGLD using an…

Machine Learning · Computer Science 2021-02-24 Difan Zou , Pan Xu , Quanquan Gu

Quantum state tomography (QST), the task of estimating an unknown quantum state given measurement outcomes, is essential to building reliable quantum computing devices. Whereas computing the maximum-likelihood (ML) estimate corresponds to…

Machine Learning · Computer Science 2022-08-30 Chien-Ming Lin , Yu-Ming Hsu , Yen-Huan Li

We use the delta method and Stein's method to derive, under regularity conditions, explicit upper bounds for the distributional distance between the distribution of the maximum likelihood estimator (MLE) of a $d$-dimensional parameter and…

Statistics Theory · Mathematics 2020-02-04 Andreas Anastasiou , Robert E. Gaunt

Likelihood-free inference methods typically make use of a distance between simulated and real data. A common example is the maximum mean discrepancy (MMD), which has previously been used for approximate Bayesian computation, minimum…

Methodology · Statistics 2023-05-11 Ayush Bharti , Masha Naslidnyk , Oscar Key , Samuel Kaski , François-Xavier Briol

We study zeroth-order optimization where solutions must minimize a cost $d(s)$ while maintaining high probability under a complex generative prior $L(s)$ (e.g., a parameterized model). This reduces to sampling from a target distribution…

Machine Learning · Computer Science 2026-05-06 Pranjal Awasthi , Sreenivas Gollapudi , Ravi Kumar , Kamesh Munagala

We advocate for a practical Maximum Likelihood Estimation (MLE) approach towards designing loss functions for regression and forecasting, as an alternative to the typical approach of direct empirical risk minimization on a specific target…

Machine Learning · Statistics 2021-10-12 Pranjal Awasthi , Abhimanyu Das , Rajat Sen , Ananda Theertha Suresh

Prior work (Klochkov $\&$ Zhivotovskiy, 2021) establishes at most $O\left(\log (n)/n\right)$ excess risk bounds via algorithmic stability for strongly-convex learners with high probability. We show that under the similar common assumptions…

Machine Learning · Computer Science 2025-10-31 Bowei Zhu , Shaojie Li , Mingyang Yi , Yong Liu

In this paper, we present near-optimal space bounds for Lp-samplers. Given a stream of updates (additions and subtraction) to the coordinates of an underlying vector x \in R^n, a perfect Lp sampler outputs the i-th coordinate with…

Data Structures and Algorithms · Computer Science 2010-12-23 Hossein Jowhari , Mert Sağlam , Gábor Tardos

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

Estimating the clutter-plus-noise covariance matrix in high-dimensional STAP is challenging in the presence of Internal Clutter Motion (ICM) and a high noise floor. The problem becomes more difficult in low-sample regimes, where the Sample…

Signal Processing · Electrical Eng. & Systems 2025-05-13 Shashwat Jain , Vikram Krishnamurthy , Muralidhar Rangaswamy , Sandeep Gogineni , Bosung Kang , Sean M. O'Rourke

We introduce the Meta Highly-Adaptive-Lasso Minimum Loss Estimator (M-HAL-MLE), a novel ensemble approach for estimating functional parameters of realistically modeled data distribution from independent and identically distributed…

Methodology · Statistics 2025-07-28 Zeyi Wang , Wenxin Zhang , Brian S Caffo , Martin Lindquist , Mark van der Laan

We establish new exponential in dimension lower bounds for the Maximum Halfspace Discrepancy problem, which models linear classification. Both are fundamental problems in computational geometry and machine learning in their exact and…

Computational Geometry · Computer Science 2026-03-20 Alexander Munteanu , Simon Omlor , Jeff M. Phillips

Every student in statistics or data science learns early on that when the sample size largely exceeds the number of variables, fitting a logistic model produces estimates that are approximately unbiased. Every student also learns that there…

Statistics Theory · Mathematics 2022-06-08 Pragya Sur , Emmanuel J. Candes

Contrastive learning is a highly successful technique for learning representations of data from labeled tuples, specifying the distance relations within the tuple. We study the sample complexity of contrastive learning, i.e. the minimum…

Machine Learning · Computer Science 2023-12-04 Noga Alon , Dmitrii Avdiukhin , Dor Elboim , Orr Fischer , Grigory Yaroslavtsev

Sampling from various kinds of distributions is an issue of paramount importance in statistics since it is often the key ingredient for constructing estimators, test procedures or confidence intervals. In many situations, the exact sampling…

Computation · Statistics 2016-12-06 Arnak S. Dalalyan

Consider a regression problem where the learner is given a large collection of $d$-dimensional data points, but can only query a small subset of the real-valued labels. How many queries are needed to obtain a $1+\epsilon$ relative error…

Machine Learning · Computer Science 2021-06-29 Xue Chen , Michał Dereziński

A new framework is introduced for examining and evaluating the fundamental limits of lossless data compression, that emphasizes genuinely non-asymptotic results. The {\em sample complexity} of compressing a given source is defined as the…

Information Theory · Computer Science 2026-04-16 Terence Viaud , Ioannis Kontoyiannis