English
Related papers

Related papers: Generalization Performance of Empirical Risk Minim…

200 papers

In this paper, we consider the problem of empirical risk minimization (ERM) of smooth, strongly convex loss functions using iterative gradient-based methods. A major goal of this literature has been to compare different algorithms, such as…

Machine Learning · Computer Science 2020-11-06 Ali Jadbabaie , Anuran Makur , Devavrat Shah

Learning Gaussian Mixture Models (GMMs) is a fundamental problem in machine learning, with the Expectation-Maximization (EM) algorithm and its popular variant gradient EM being arguably the most widely used algorithms in practice. In the…

Machine Learning · Computer Science 2025-06-10 Mo Zhou , Weihang Xu , Maryam Fazel , Simon S. Du

We revisit the problem of learning a single neuron with ReLU activation under Gaussian input with square loss. We particularly focus on the over-parameterization setting where the student network has $n\ge 2$ neurons. We prove the global…

Machine Learning · Computer Science 2023-10-11 Weihang Xu , Simon S. Du

In this paper, we theoretically prove that gradient descent can find a global minimum of non-convex optimization of all layers for nonlinear deep neural networks of sizes commonly encountered in practice. The theory developed in this paper…

Machine Learning · Statistics 2020-06-18 Kenji Kawaguchi , Jiaoyang Huang

Given a collection of feature maps indexed by a set $\mathcal{T}$, we study the performance of empirical risk minimization (ERM) on regression problems with square loss over the union of the linear classes induced by these feature maps.…

Machine Learning · Statistics 2024-11-20 Ayoub El Hanchi , Chris J. Maddison , Murat A. Erdogdu

We establish empirical risk minimization principles for active learning by deriving a family of upper bounds on the generalization error. Aligning with empirical observations, the bounds suggest that superior query algorithms can be…

Machine Learning · Statistics 2024-09-17 Vincent Menden , Yahya Saleh , Armin Iske

We study the loss landscape of both shallow and deep, mildly overparameterized ReLU neural networks on a generic finite input dataset for the squared error loss. We show both by count and volume that most activation patterns correspond to…

Machine Learning · Computer Science 2024-02-09 Kedar Karhadkar , Michael Murray , Hanna Tseran , Guido Montúfar

This paper follows up on a recent work of Neu et al. (2021) and presents some new information-theoretic upper bounds for the generalization error of machine learning models, such as neural networks, trained with SGD. We apply these bounds…

Machine Learning · Computer Science 2022-03-22 Ziqiao Wang , Yongyi Mao

Consider the empirical risk minimization (ERM) problem, which is stated as follows. Let $K_1, \dots, K_m$ be compact convex sets with $K_i \subseteq \mathbb{R}^{n_i}$ for $i \in [m]$, $n = \sum_{i=1}^m n_i$, and $n_i\le C_K$ for some…

Data Structures and Algorithms · Computer Science 2025-12-02 Yang P. Liu , Richard Peng , Colin Tang , Albert Weng , Junzhao Yang

This work focuses on the behavior of stochastic gradient descent (SGD) in solving least-squares regression with physics-informed neural networks (PINNs). Past work on this topic has been based on the over-parameterization regime, whose…

Machine Learning · Computer Science 2025-07-23 Zhihan Zeng , Yiqi Gu

In a wide range of statistical learning problems such as ranking, clustering or metric learning among others, the risk is accurately estimated by $U$-statistics of degree $d\geq 1$, i.e. functionals of the training data with low variance…

Machine Learning · Statistics 2019-01-25 Stéphan Clémençon , Aurélien Bellet , Igor Colin

We show that the empirical risk minimization (ERM) problem for neural networks has no solution in general. Given a training set $s_1, \dots, s_n \in \mathbb{R}^p$ with corresponding responses $t_1,\dots,t_n \in \mathbb{R}^q$, fitting a…

Machine Learning · Computer Science 2019-12-13 Lek-Heng Lim , Mateusz Michalek , Yang Qi

One of the mysteries in the success of neural networks is randomly initialized first order methods like gradient descent can achieve zero training loss even though the objective function is non-convex and non-smooth. This paper demystifies…

Machine Learning · Computer Science 2019-02-06 Simon S. Du , Xiyu Zhai , Barnabas Poczos , Aarti Singh

We study the gradient Expectation-Maximization (EM) algorithm for Gaussian Mixture Models (GMM) in the over-parameterized setting, where a general GMM with $n>1$ components learns from data that are generated by a single ground truth…

Machine Learning · Computer Science 2025-06-03 Weihang Xu , Maryam Fazel , Simon S. Du

Model-based neural networks provide unparalleled performance for various tasks, such as sparse coding and compressed sensing problems. Due to the strong connection with the sensing model, these networks are interpretable and inherit prior…

Machine Learning · Computer Science 2023-04-20 Avner Shultzman , Eyar Azar , Miguel R. D. Rodrigues , Yonina C. Eldar

We study model evaluation and model selection from the perspective of generalization ability (GA): the ability of a model to predict outcomes in new samples from the same population. We believe that GA is one way formally to address…

Machine Learning · Statistics 2016-10-19 Ning Xu , Jian Hong , Timothy C. G. Fisher

The development of new classification and regression algorithms based on empirical risk minimization (ERM) over deep neural network hypothesis classes, coined deep learning, revolutionized the area of artificial intelligence, machine…

Machine Learning · Computer Science 2020-11-12 Julius Berner , Philipp Grohs , Arnulf Jentzen

We propose a general framework for deriving generalization bounds for parallel positively homogeneous neural networks--a class of neural networks whose input-output map decomposes as the sum of positively homogeneous maps. Examples of such…

Machine Learning · Computer Science 2025-03-20 Uday Kiran Reddy Tadipatri , Benjamin D. Haeffele , Joshua Agterberg , René Vidal

Several works have aimed to explain why overparameterized neural networks generalize well when trained by Stochastic Gradient Descent (SGD). The consensus explanation that has emerged credits the randomized nature of SGD for the bias of the…

Machine Learning · Computer Science 2021-02-24 Shengchao Liu , Dimitris Papailiopoulos , Dimitris Achlioptas

Recent works have cast some light on the mystery of why deep nets fit any data and generalize despite being very overparametrized. This paper analyzes training and generalization for a simple 2-layer ReLU net with random initialization, and…

Machine Learning · Computer Science 2019-05-28 Sanjeev Arora , Simon S. Du , Wei Hu , Zhiyuan Li , Ruosong Wang