English
Related papers

Related papers: Minimax rate of consistency for linear models with…

200 papers

For many machine learning tasks, the input data lie on a low-dimensional manifold embedded in a high dimensional space and, because of this high-dimensional structure, most algorithms are inefficient. The typical solution is to reduce the…

Machine Learning · Computer Science 2019-03-05 Anna C. Gilbert , Rishi Sonthalia

Conditions ensuring optimal parameter estimation in the presence of missing data are well established in inference, typically relying on the Missing-at-Random (MAR) assumption. In prediction, similar principles are often assumed to apply.…

Methodology · Statistics 2026-03-19 Pierre Catoire , Robin Genuer , Cecile Proust-Lima

High-dimensional models often have a large memory footprint and must be quantized after training before being deployed on resource-constrained edge devices for inference tasks. In this work, we develop an information-theoretic framework for…

Information Theory · Computer Science 2022-09-01 Rajarshi Saha , Mert Pilanci , Andrea J. Goldsmith

Nonignorable missing outcomes are common in real world datasets and often require strong parametric assumptions to achieve identification. These assumptions can be implausible or untestable, and so we may forgo them in favour of partially…

Methodology · Statistics 2023-10-19 Daniel Daly-Grafstein , Paul Gustafson

This paper is concerned with general nonlinear regression models where the predictor variables are subject to Berkson-type measurement errors. The measurement errors are assumed to have a general parametric distribution, which is not…

Statistics Theory · Mathematics 2009-08-21 Liqun Wang

Under a standard assumption in complexity theory (NP not in P/poly), we demonstrate a gap between the minimax prediction risk for sparse linear regression that can be achieved by polynomial-time algorithms, and that achieved by optimal…

Statistics Theory · Mathematics 2014-05-22 Yuchen Zhang , Martin J. Wainwright , Michael I. Jordan

The bias-variance trade-off is a central concept in supervised learning. In classical statistics, increasing the complexity of a model (e.g., number of parameters) reduces bias but also increases variance. Until recently, it was commonly…

Machine Learning · Statistics 2022-03-25 Jason W. Rocks , Pankaj Mehta

We introduce new online and batch algorithms that are robust to data with missing features, a situation that arises in many practical applications. In the online setup, we allow for the comparison hypothesis to change as a function of the…

Machine Learning · Computer Science 2012-02-19 Afshin Rostamizadeh , Alekh Agarwal , Peter Bartlett

The exploration of complex physical or technological processes usually requires exploiting available information from different sources: (i) physical laws often represented as a family of parameter dependent partial differential equations…

Numerical Analysis · Mathematics 2020-02-04 Albert Cohen , Wolfgang Dahmen , Ron DeVore

One limitation of the most statistical/machine learning-based variable selection approaches is their inability to control the false selections. A recently introduced framework, model-x knockoffs, provides that to a wide range of models but…

Machine Learning · Statistics 2025-09-03 Deniz Koyuncu , Alex Gittens , Bülent Yener

For some estimations and predictions, we solve minimization problems with asymmetric loss functions. Usually, we estimate the coefficient of regression for these problems. In this paper, we do not make such the estimation, but rather give a…

Statistics Theory · Mathematics 2023-03-03 Naoya Yamaguchi , Yuka Yamaguchi , Ryuei Nishii

A wide array of machine learning problems are formulated as the minimization of the expectation of a convex loss function on some parameter space. Since the probability distribution of the data of interest is usually unknown, it is is often…

Optimization and Control · Mathematics 2019-05-27 Emilie Chouzenoux , Henri Gérard , Jean-Christophe Pesquet

We investigate methods for parameter learning from incomplete data that is not missing at random. Likelihood-based methods then require the optimization of a profile likelihood that takes all possible missingness mechanisms into account.…

Methodology · Statistics 2012-07-02 Manfred Jaeger

This book is meant to provide an introduction to linear models and the theories behind them. Our goal is to give a rigorous introduction to the readers with prior exposure to ordinary least squares. In machine learning, the output is…

Machine Learning · Computer Science 2025-05-12 Jun Lu

This work addresses the problem of missing data in time-series analysis focusing on (a) estimation of model parameters in the presence of missing data and (b) reconstruction of missing data. Standard approaches used to solve these problems…

Methodology · Statistics 2020-01-01 Dimitri Igdalov , Olga Kaiser , Ilia Horenko

We construct a classifier which attains the rate of convergence $\log n/n$ under sparsity and margin assumptions. An approach close to the one met in approximation theory for the estimation of function is used to obtain this result. The…

Statistics Theory · Mathematics 2016-08-16 Guillaume Lecué

While mixture of linear regressions (MLR) is a well-studied topic, prior works usually do not analyze such models for prediction error. In fact, {\em prediction} and {\em loss} are not well-defined in the context of mixtures. In this paper,…

Machine Learning · Statistics 2022-05-27 Avishek Ghosh , Arya Mazumdar , Soumyabrata Pal , Rajat Sen

We consider the problem of designing minimax estimators for estimating the parameters of a probability distribution. Unlike classical approaches such as the MLE and minimum distance estimators, we consider an algorithmic approach for…

Machine Learning · Statistics 2020-06-23 Kartik Gupta , Arun Sai Suggala , Adarsh Prasad , Praneeth Netrapalli , Pradeep Ravikumar

Motivated by the increasing use of and rapid changes in array technologies, we consider the prediction problem of fitting a linear regression relating a continuous outcome $Y$ to a large number of covariates $\mathbf {X}$, for example,…

Applications · Statistics 2014-01-13 Philip S. Boonstra , Bhramar Mukherjee , Jeremy M. G. Taylor

Supervised learning methods with missing data have been extensively studied not just due to the techniques related to low-rank matrix completion. Also in unsupervised learning one often relies on imputation methods. As a matter of fact,…

Statistics Theory · Mathematics 2018-11-27 Andreas Elsener , Sara van de Geer