English
Related papers

Related papers: All ERMs Can Fail in Stochastic Convex Optimizatio…

200 papers

Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study…

Optimization and Control · Mathematics 2018-10-30 Lenaic Chizat , Francis Bach

We examine the relationship between the mutual information between the output model and the empirical sample and the generalization of the algorithm in the context of stochastic convex optimization. Despite increasing interest in…

Machine Learning · Computer Science 2024-01-17 Roi Livni

Differentially private empirical risk minimization (DP-ERM) is a fundamental problem in private optimization. While the theory of DP-ERM is well-studied, as large-scale models become prevalent, traditional DP-ERM methods face new…

Machine Learning · Computer Science 2024-06-05 Yin Tat Lee , Daogao Liu , Zhou Lu

We investigate 1) the rate at which refined properties of the empirical risk---in particular, gradients---converge to their population counterparts in standard non-convex learning tasks, and 2) the consequences of this convergence for…

Machine Learning · Computer Science 2018-11-13 Dylan J. Foster , Ayush Sekhari , Karthik Sridharan

We study high-dimensional convex empirical risk minimization (ERM) under general non-Gaussian data designs. By heuristically extending the Convex Gaussian Min-Max Theorem (CGMT) to non-Gaussian settings, we derive an asymptotic min-max…

Machine Learning · Statistics 2026-04-06 Chiheb Yaakoubi , Cosme Louart , Malik Tiomoko , Zhenyu Liao

We study the sample complexity of stochastic convex optimization when problem parameters, e.g., the distance to optimality, are unknown. We pursue two strategies. First, we develop a reliable model selection method that avoids overfitting…

Machine Learning · Computer Science 2025-06-16 Jared Lawrence , Ari Kalinsky , Hannah Bradfield , Yair Carmon , Oliver Hinder

Stochastic convex optimization over an $\ell_1$-bounded domain is ubiquitous in machine learning applications such as LASSO but remains poorly understood when learning with differential privacy. We show that, up to logarithmic factors the…

Machine Learning · Computer Science 2021-03-03 Hilal Asi , Vitaly Feldman , Tomer Koren , Kunal Talwar

Fitting a function by using linear combinations of a large number $N$ of `simple' components is one of the most fruitful ideas in statistical learning. This idea lies at the core of a variety of methods, from two-layer neural networks to…

Statistics Theory · Mathematics 2019-08-20 Adel Javanmard , Marco Mondelli , Andrea Montanari

Minimizing the empirical risk is a popular training strategy, but for learning tasks where the data may be noisy or heavy-tailed, one may require many observations in order to generalize well. To achieve better performance under less…

Machine Learning · Statistics 2018-10-16 Matthew J. Holland , Kazushi Ikeda

Gibbs-ERM learning is a natural idealized model of learning with stochastic optimization algorithms (such as Stochastic Gradient Langevin Dynamics and ---to some extent--- Stochastic Gradient Descent), while it also arises in other…

Machine Learning · Computer Science 2019-02-06 Ilja Kuzborskij , Nicolò Cesa-Bianchi , Csaba Szepesvári

Error bound conditions (EBC) are properties that characterize the growth of an objective function when a point is moved away from the optimal set. They have recently received increasing attention in the field of optimization for developing…

Machine Learning · Statistics 2018-05-15 Mingrui Liu , Xiaoxuan Zhang , Lijun Zhang , Rong Jin , Tianbao Yang

In this paper, we study the generalization performance of global minima for implementing empirical risk minimization (ERM) on over-parameterized deep ReLU nets. Using a novel deepening scheme for deep ReLU nets, we rigorously prove that…

Machine Learning · Computer Science 2023-03-01 Shao-Bo Lin , Yao Wang , Ding-Xuan Zhou

In this work and the supporting Part II, we examine the performance of stochastic sub-gradient learning strategies under weaker conditions than usually considered in the literature. The new conditions are shown to be automatically satisfied…

Machine Learning · Statistics 2017-04-24 Bicheng Ying , Ali H. Sayed

We study randomized algorithms for constrained optimization, in abstract frameworks that include, in strictly increasing generality: convex programming; LP-type problems; violator spaces; and a setting we introduce, consistent spaces. Such…

Computational Geometry · Computer Science 2019-06-04 Kenneth L. Clarkson , Bernd Gärtner , Johannes Lengler , May Szedlak

Establishing a theoretical analysis that explains why deep learning can outperform shallow learning such as kernel methods is one of the biggest issues in the deep learning literature. Towards answering this question, we evaluate excess…

Machine Learning · Statistics 2020-12-08 Taiji Suzuki , Shunta Akiyama

In this paper, we address learning problems for high dimensional data. Previously, oblivious random projection based approaches that project high dimensional features onto a random subspace have been used in practice for tackling…

Machine Learning · Computer Science 2016-12-07 Yi Xu , Haiqin Yang , Lijun Zhang , Tianbao Yang

We study in this paper lower bounds for the generalization error of models derived from multi-layer neural networks, in the regime where the size of the layers is commensurate with the number of samples in the training data. We show that…

Machine Learning · Statistics 2022-07-08 Inbar Seroussi , Ofer Zeitouni

Classic supervised learning involves algorithms trained on $n$ labeled examples to produce a hypothesis $h \in \mathcal{H}$ aimed at performing well on unseen examples. Meta-learning extends this by training across $n$ tasks, with $m$…

Machine Learning · Statistics 2024-11-28 Yannay Alon , Steve Hanneke , Shay Moran , Uri Shalit

We consider learning methods based on the regularization of a convex empirical risk by a squared Hilbertian norm, a setting that includes linear predictors and non-linear predictors through positive-definite kernels. In order to go beyond…

Machine Learning · Computer Science 2019-06-19 Ulysse Marteau-Ferey , Dmitrii Ostrovskii , Francis Bach , Alessandro Rudi

Understanding the generalization behavior of learning algorithms is a central goal of learning theory. A recently emerging explanation is that learning algorithms are successful in practice because they converge to flat minima, which have…

Machine Learning · Computer Science 2026-05-26 Matan Schliserman , Shira Vansover-Hager , Tomer Koren