English
Related papers

Related papers: Learning Orthogonal Multi-Index Models: A Fine-Gra…

200 papers

Dictionary learning is the task of determining a data-dependent transform that yields a sparse representation of some observed data. The dictionary learning problem is non-convex, and usually solved via computationally complex iterative…

Machine Learning · Computer Science 2016-11-30 Cristian Rusu , Nuria Gonzalez-Prelcic , Robert Heath

In this work we consider generic Gaussian Multi-index models, in which the labels only depend on the (Gaussian) $d$-dimensional inputs through their projection onto a low-dimensional $r = O_d(1)$ subspace, and we study efficient agnostic…

Machine Learning · Computer Science 2025-06-09 Alex Damian , Jason D. Lee , Joan Bruna

Modern machine learning is trained by stochastic gradient descent (SGD), whose performance critically depends on how the learning rate (LR) is adjusted and decreased over time. Yet existing LR regimes may be intricate, or need to tune one…

Machine Learning · Computer Science 2025-08-20 Zhuang Yang

We study the problem of learning a low-degree spherical polynomial of degree $\ell_0 = \Theta(1) \ge 1$ defined on the unit sphere in $\RR^d$ by training an over-parameterized two-layer neural network (NN) with channel attention in this…

Machine Learning · Statistics 2026-04-28 Yingzhen Yang

This work investigates the performance of the final iterate produced by stochastic gradient descent (SGD) under temporally dependent data. We consider two complementary sources of dependence: $(i)$ martingale-type dependence in both the…

Statistics Theory · Mathematics 2026-01-06 Yinan Shen , Yichen Zhang , Wen-Xin Zhou

We study convergence properties of Stochastic Gradient Descent (SGD) for convex objectives without assumptions on smoothness or strict convexity. We consider the question of establishing that with high probability the objective evaluated at…

Machine Learning · Computer Science 2018-10-23 Andrea Schioppa

The representation of functions by artificial neural networks depends on a large number of parameters in a non-linear fashion. Suitable parameters of these are found by minimizing a 'loss functional', typically by stochastic gradient…

Machine Learning · Computer Science 2021-09-16 Stephan Wojtowytsch

Recent work has shown that removing orthogonalization during training and applying it only at inference improves rotation estimation in deep learning, with empirical evidence favoring 9D representations with SVD projection. However, the…

Machine Learning · Computer Science 2026-04-08 Chris Choy

This paper introduces \texttt{FedMPDD} (\textbf{Fed}erated Learning via \textbf{M}ulti-\textbf{P}rojected \textbf{D}irectional \textbf{D}erivatives), a novel algorithm that simultaneously optimizes bandwidth utilization and enhances privacy…

Machine Learning · Computer Science 2025-12-25 Mohammadreza Rostami , Solmaz S. Kia

Performative distribution shift captures the setting where the choice of which ML model is deployed changes the data distribution. For example, a bank which uses the number of open credit lines to determine a customer's risk of default on a…

Machine Learning · Computer Science 2021-02-17 Zachary Izzo , Lexing Ying , James Zou

This paper deals with model-order reduction of parametric partial differential equations (PPDE). More specifically, we consider the problem of finding a good approximation subspace of the solution manifold of the PPDE when only partial…

Numerical Analysis · Mathematics 2017-07-04 C. Herzet , P. Héas , A. Drémeau

Risk minimization for nonsmooth nonconvex problems naturally leads to first-order sampling or, by an abuse of terminology, to stochastic subgradient descent. We establish the convergence of this method in the path-differentiable case and…

Optimization and Control · Mathematics 2024-07-24 Jérôme Bolte , Tam Le , Edouard Pauwels

Detecting out-of-distribution (OOD) data is crucial for ensuring the safe deployment of machine learning models in real-world applications. However, existing OOD detection approaches primarily rely on the feature maps or the full gradient…

Computer Vision and Pattern Recognition · Computer Science 2023-08-02 Sima Behpour , Thang Doan , Xin Li , Wenbin He , Liang Gou , Liu Ren

We obtain a tight distribution-specific characterization of the sample complexity of large-margin classification with L2 regularization: We introduce the margin-adapted dimension, which is a simple function of the second order statistics of…

Machine Learning · Statistics 2013-09-19 Sivan Sabato , Nathan Srebro , Naftali Tishby

We study a general class of bilevel problems, consisting in the minimization of an upper-level objective which depends on the solution to a parametric fixed-point equation. Important instances arising in machine learning include…

Machine Learning · Statistics 2020-07-13 Riccardo Grazzi , Luca Franceschi , Massimiliano Pontil , Saverio Salzo

Multi-layer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding. Learning a neural network requires to optimize a non-convex high-dimensional…

Machine Learning · Statistics 2022-06-08 Song Mei , Andrea Montanari , Phan-Minh Nguyen

Differentially Private Stochastic Gradient Descent (DP-SGD) limits the amount of private information deep learning models can memorize during training. This is achieved by clipping and adding noise to the model's gradients, and thus…

Computer Vision and Pattern Recognition · Computer Science 2023-06-22 Florian A. Hölzl , Daniel Rueckert , Georgios Kaissis

Orthogonal statistical learning and double machine learning have emerged as general frameworks for two-stage statistical prediction in the presence of a nuisance component. We establish non-asymptotic bounds on the excess risk of orthogonal…

Machine Learning · Statistics 2022-06-22 Lang Liu , Carlos Cinelli , Zaid Harchaoui

Deep neural networks are a promising approach towards multi-task learning because of their capability to leverage knowledge across domains and learn general purpose representations. Nevertheless, they can fail to live up to these promises…

Machine Learning · Computer Science 2019-12-17 Mihai Suteu , Yike Guo

This paper investigates the convergence properties of the hypergradient descent method (HDM), a 25-year-old heuristic originally proposed for adaptive stepsize selection in stochastic first-order methods. We provide the first rigorous…

Optimization and Control · Mathematics 2025-03-18 Ya-Chi Chu , Wenzhi Gao , Yinyu Ye , Madeleine Udell