English
Related papers

Related papers: Agnostic Sample Compression Schemes for Regression

200 papers

Modern machine learning classifiers often exhibit vanishing classification error on the training set. They achieve this by learning nonlinear representations of the inputs that maps the data into linearly separable classes. Motivated by…

Statistics Theory · Mathematics 2023-03-23 Andrea Montanari , Feng Ruan , Youngtak Sohn , Jun Yan

We investigate the problem of testing the global null in the high-dimensional regression models when the feature dimension $p$ grows proportionally to the number of observations $n$. Despite a number of prior work studying this problem,…

Methodology · Statistics 2020-10-06 Yue Li , Ilmun Kim , Yuting Wei

We give a row sampling algorithm for the quantile loss function with sample complexity nearly linear in the dimensionality of the data, improving upon the previous best algorithm whose sampling complexity has at least cubic dependence on…

Data Structures and Algorithms · Computer Science 2020-06-16 Yi Li , Ruosong Wang , Lin Yang , Hanrui Zhang

Over the last decade, approximating functions in infinite dimensions from samples has gained increasing attention in computational science and engineering, especially in computational uncertainty quantification. This is primarily due to the…

Numerical Analysis · Mathematics 2023-10-18 Ben Adcock , Nick Dexter , Sebastian Moraga

In this work we investigate the generalization performance of random feature ridge regression (RFRR). Our main contribution is a general deterministic equivalent for the test error of RFRR. Specifically, under a certain concentration…

Machine Learning · Statistics 2024-11-06 Leonardo Defilippis , Bruno Loureiro , Theodor Misiakiewicz

We consider the problem of linear regression where the $\ell_2^n$ norm loss (i.e., the usual least squares loss) is replaced by the $\ell_p^n$ norm. We show how to solve such problems up to machine precision in $O^*(n^{|1/2 - 1/p|})$…

Optimization and Control · Mathematics 2018-06-26 Sébastien Bubeck , Michael B. Cohen , Yin Tat Lee , Yuanzhi Li

The Sample Compression Conjecture of Littlestone & Warmuth has remained unsolved for over two decades. This paper presents a systematic geometric investigation of the compression of finite maximum concept classes. Simple arrangements of…

Machine Learning · Computer Science 2014-02-04 Benjamin I. P. Rubinstein , J. Hyam Rubinstein

We study the problem of agnostic learning under the Gaussian distribution. We develop a method for finding hard families of examples for a wide class of problems by using LP duality. For Boolean-valued concept classes, we show that the…

Machine Learning · Computer Science 2021-02-09 Ilias Diakonikolas , Daniel M. Kane , Thanasis Pittas , Nikos Zarifis

Recent works in dimensionality reduction for regression tasks have introduced the notion of sensitivity, an estimate of the importance of a specific datapoint in a dataset, offering provable guarantees on the quality of the approximation…

Machine Learning · Computer Science 2023-11-22 Swati Padmanabhan , David P. Woodruff , Qiuyi Zhang

We study the optimal scale at which real-valued function classes exhibit uniform convergence and learnability. Our main result establishes a scale-sensitive generalization of the fundamental theorem of PAC learning: for every bounded…

Machine Learning · Computer Science 2026-05-14 Shashaank Aiyer , Yishay Mansour , Shay Moran , Han Shao , Tom Waknine

Model quantization has become essential for efficient large language model deployment, yet existing approaches involve clear trade-offs: methods such as GPTQ and AWQ achieve practical compression but are lossy, while lossless techniques…

Machine Learning · Computer Science 2026-05-05 Michael Helcig , Eldar Kurtic , Dan Alistarh

The density weighted average derivative (DWAD) of a regression function is a canonical parameter of interest in economics. Classical first-order large sample distribution theory for kernel-based DWAD estimators relies on tuning parameter…

Econometrics · Economics 2024-02-16 Matias D. Cattaneo , Max H. Farrell , Michael Jansson , Ricardo Masini

The predictive quality of machine learning models is typically measured in terms of their (approximate) expected prediction accuracy or the so-called Area Under the Curve (AUC). Minimizing the reciprocals of these measures are the goals of…

Machine Learning · Statistics 2019-03-04 Hiva Ghanbari , Minhan Li , Katya Scheinberg

Linear regression models are useful statistical tools to analyze data sets in several different fields. There are several methods to estimate the parameters of a linear regression model. These methods usually perform under normally…

Methodology · Statistics 2020-08-10 Şenay Özdemir , Yeşim Güney , Yetkin Tuaç , Olcay Arslan

We study approximation of the embedding $\ell_p^m \rightarrow \ell_{\infty}^m$, $1 \leq p \leq 2$, based on randomized adaptive algorithms that use arbitrary linear functionals as information on a problem instance. We show upper bounds for…

Numerical Analysis · Mathematics 2024-08-05 Robert J. Kunsch , Marcin Wnuk

Understanding efficiency in high dimensional linear models is a longstanding problem of interest. Classical work with smaller dimensional problems dating back to Huber and Bickel has illustrated the benefits of efficient loss functions.…

Statistics Theory · Mathematics 2017-08-16 Jelena Bradic

The recent work by Dong & Yang (2023) showed for misspecified sparse linear bandits, one can obtain an $O\left(\epsilon\right)$-optimal policy using a polynomial number of samples when the sparsity is a constant, where $\epsilon$ is the…

Machine Learning · Computer Science 2024-07-19 Ally Yalei Du , Lin F. Yang , Ruosong Wang

The Johnson-Lindenstrauss (JL) lemma is a fundamental result in dimensionality reduction, ensuring that any finite set $X \subseteq \mathbb{R}^d$ can be embedded into a lower-dimensional space $\mathbb{R}^k$ while approximately preserving…

Probability · Mathematics 2025-10-30 Rafael Chiclana , Mark Iwen

We establish minimax convergence rates for classification of functional data and for nonparametric regression with functional design variables. The optimal rates are of logarithmic type under smoothness constraints on the functional density…

Statistics Theory · Mathematics 2016-03-31 Alexander Meister

In this paper we extend results taken from compressed sensing to recover Hilbert-space valued vectors. This is an important problem in parametric function approximation in particular when the number of parameters is high. By expanding our…

Numerical Analysis · Mathematics 2020-06-09 Jean-Luc Bouchot
‹ Prev 1 4 5 6 7 8 10 Next ›