English
Related papers

Related papers: A Regularization-Sharpness Tradeoff for Linear Int…

200 papers

We formulate a principle for classification with the knowledge of the marginal distribution over the data points (unlabeled data). The principle is cast in terms of Tikhonov style regularization where the regularization penalty articulates…

Machine Learning · Computer Science 2012-12-12 Adrian Corduneanu , Tommi S. Jaakkola

We study multi-parameter regularization (multiple penalties) for solving linear inverse problems to promote simultaneously distinct features of the sought-for objects. We revisit a balancing principle for choosing regularization parameters…

Numerical Analysis · Mathematics 2013-06-26 Kazufumi Ito , Bangti Jin , Tomoya Takeuchi

The classical bias-variance trade-off predicts that bias decreases and variance increase with model complexity, leading to a U-shaped risk curve. Recent work calls this into question for neural networks and other over-parameterized models,…

Machine Learning · Computer Science 2020-12-09 Zitong Yang , Yaodong Yu , Chong You , Jacob Steinhardt , Yi Ma

The bias-variance tradeoff tells us that as model complexity increases, bias falls and variances increases, leading to a U-shaped test error curve. However, recent empirical results with over-parameterized neural networks are marked by a…

Interpolators -- estimators that achieve zero training error -- have attracted growing attention in machine learning, mainly because state-of-the art neural networks appear to be models of this type. In this paper, we study minimum $\ell_2$…

Statistics Theory · Mathematics 2022-09-12 Trevor Hastie , Andrea Montanari , Saharon Rosset , Ryan J. Tibshirani

Iteratively reweighted least square (IRLS) is a popular approach to solve sparsity-enforcing regression problems in machine learning. State of the art approaches are more efficient but typically rely on specific coordinate pruning schemes.…

Machine Learning · Statistics 2022-10-03 Clarice Poon , Gabriel Peyré

A recent line of work has shown that an overparametrized neural network can perfectly fit the training data, an otherwise often intractable nonconvex optimization problem. For (fully-connected) shallow networks, in the best case scenario,…

Machine Learning · Computer Science 2019-10-30 Armin Eftekhari , ChaeHwan Song , Volkan Cevher

Optimization problems over permutation matrices appear widely in facility layout, chip design, scheduling, pattern recognition, computer vision, graph matching, etc. Since this problem is NP-hard due to the combinatorial nature of…

Optimization and Control · Mathematics 2016-09-01 Bo Jiang , Ya-Feng Liu , Zaiwen Wen

The $\ell_{1\text{-}2}$ regularization method has a strong sparsity promoting capability in approaching sparse solutions of linear inverse problems and gained successful applications in various mathematics and applied science fields. This…

Optimization and Control · Mathematics 2026-03-04 Yaohua Hu , Hao Wang , Xiaoqi Yang

In this paper, we study norm-based regularization methods for neural networks. We compare existing penalization approaches and introduce two regularization strategies that extend classical ridge- and lasso-type penalties to neural network…

Machine Learning · Statistics 2026-05-04 Muhammad Qasim , Farrukh Javed

Pruning neural network parameters is often viewed as a means to compress models, but pruning has also been motivated by the desire to prevent overfitting. This motivation is particularly relevant given the perhaps surprising observation…

Machine Learning · Computer Science 2020-10-26 Brian R. Bartoldson , Ari S. Morcos , Adrian Barbu , Gordon Erlebacher

In this paper we characterize sharp time-data tradeoffs for optimization problems used for solving linear inverse problems. We focus on the minimization of a least-squares objective subject to a constraint defined as the sub-level set of a…

Information Theory · Computer Science 2016-01-06 Samet Oymak , Benjamin Recht , Mahdi Soltanolkotabi

We investigate implicit regularization schemes for gradient descent methods applied to unpenalized least squares regression to solve the problem of reconstructing a sparse signal from an underdetermined system of linear measurements under…

Machine Learning · Statistics 2019-09-12 Tomas Vaškevičius , Varun Kanade , Patrick Rebeschini

Classical wisdom in machine learning holds that the generalization error can be decomposed into bias and variance, and these two terms exhibit a \emph{trade-off}. However, in this paper, we show that for an ensemble of deep learning based…

Machine Learning · Computer Science 2023-10-16 Lin Chen , Michal Lukasik , Wittawat Jitkrittum , Chong You , Sanjiv Kumar

A continuing mystery in understanding the empirical success of deep neural networks is their ability to achieve zero training error and generalize well, even when the training data is noisy and there are more parameters than data points. We…

Machine Learning · Computer Science 2019-09-10 Vidya Muthukumar , Kailas Vodrahalli , Vignesh Subramanian , Anant Sahai

Increasing utilization of machine learning based decision support systems emphasizes the need for resulting predictions to be both accurate and fair to all stakeholders. In this work we present a novel approach to increase a Neural Network…

Machine Learning · Computer Science 2021-11-08 Bhanu Jain , Manfred Huber , Ramez Elmasri

Sparse regularization is a central technique for both machine learning (to achieve supervised features selection or unsupervised mixture learning) and imaging sciences (to achieve super-resolution). Existing performance guaranties assume a…

Information Theory · Computer Science 2018-10-09 Clarice Poon , Nicolas Keriven , Gabriel Peyré

Using the $\ell_1$-norm to regularize the estimation of the parameter vector of a linear model leads to an unstable estimator when covariates are highly correlated. In this paper, we introduce a new penalty function which takes into account…

Machine Learning · Computer Science 2011-09-14 Edouard Grave , Guillaume Obozinski , Francis Bach

Deep neural networks exploiting millions of parameters are nowadays the norm in deep learning applications. This is a potential issue because of the great amount of computational resources needed for training, and of the possible loss of…

Computation and Language · Computer Science 2022-10-31 Giovanni Bonetta , Matteo Ribero , Rossella Cancelliere

The Least Absolute Shrinkage and Selection Operator (LASSO) has gained attention in a wide class of continuous parametric estimation problems with promising results. It has been a subject of research for more than a decade. Due to the…

Computation · Statistics 2015-04-13 Ashkan Panahi , Mats Viberg