English
Related papers

Related papers: Reliably Learning the ReLU in Polynomial Time

200 papers

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 develop fast algorithms and robust software for convex optimization of two-layer neural networks with ReLU activation functions. Our work leverages a convex reformulation of the standard weight-decay penalized training problem as a set…

Machine Learning · Computer Science 2025-04-10 Aaron Mishkin , Arda Sahiner , Mert Pilanci

This paper presents an efficient algorithm for robust network reconstruction of Linear Time-Invariant (LTI) systems in the presence of noise, estimation errors and unmodelled nonlinearities. The method here builds on previous work on robust…

Dynamical Systems · Mathematics 2016-11-18 David Hayden , Ye Yuan , Jorge Gonçalves

We study the task of learning latent-variable models. A common algorithmic technique for this task is the method of moments. Unfortunately, moment-based approaches are hampered by the fact that the moment tensors of super-constant degree…

Data Structures and Algorithms · Computer Science 2025-04-15 Ilias Diakonikolas , Daniel M. Kane

It is shown that over-parameterized neural networks can achieve minimax optimal rates of convergence (up to logarithmic factors) for learning functions from certain smooth function classes, if the weights are suitably constrained or…

Machine Learning · Statistics 2024-06-05 Yunfei Yang , Ding-Xuan Zhou

Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current robust loss functions, however, inevitably involve hyperparameter(s) to be tuned, manually or heuristically through cross…

Machine Learning · Computer Science 2020-02-18 Jun Shu , Qian Zhao , Keyu Chen , Zongben Xu , Deyu Meng

Each year, deep learning demonstrates new and improved empirical results with deeper and wider neural networks. Meanwhile, with existing theoretical frameworks, it is difficult to analyze networks deeper than two layers without resorting to…

Machine Learning · Computer Science 2023-03-28 Hong Jun Jeon , Yifan Zhu , Benjamin Van Roy

When optimizing a nonlinear objective, one can employ a neural network as a surrogate for the nonlinear function. However, the resulting optimization model can be time-consuming to solve globally with exact methods. As a result, local…

Optimization and Control · Mathematics 2026-03-19 Jiatai Tong , Yilin Zhu , Thiago Serra , Samuel Burer

Outsourcing deep neural networks (DNNs) inference tasks to an untrusted cloud raises data privacy and integrity concerns. While there are many techniques to ensure privacy and integrity for polynomial-based computations, DNNs involve…

Machine Learning · Computer Science 2024-02-07 Ramy E. Ali , Jinhyun So , A. Salman Avestimehr

We study the necessary and sufficient complexity of ReLU neural networks---in terms of depth and number of weights---which is required for approximating classifier functions in $L^2$. As a model class, we consider the set $\mathcal{E}^\beta…

Functional Analysis · Mathematics 2018-05-23 Philipp Petersen , Felix Voigtlaender

Neural networks are usually trained with different variants of gradient descent based optimization algorithms such as stochastic gradient descent or the Adam optimizer. Recent theoretical work states that the critical points (where the…

Machine Learning · Computer Science 2024-10-15 Adrian Barbu

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

We consider the dynamic of gradient descent for learning a two-layer neural network. We assume the input $x\in\mathbb{R}^d$ is drawn from a Gaussian distribution and the label of $x$ satisfies $f^{\star}(x) = a^{\top}|W^{\star}x|$, where…

Machine Learning · Computer Science 2020-07-10 Yuanzhi Li , Tengyu Ma , Hongyang R. Zhang

In this paper, we focus on fully connected deep neural networks utilizing the Rectified Linear Unit (ReLU) activation function for nonparametric estimation. We derive non-asymptotic bounds that lead to convergence rates, addressing both…

We study the Rectified Linear Unit (ReLU) dual, an existing dual formulation for stochastic programs that reformulates non-anticipativity constraints using ReLU functions to generate tight, non-convex, and mixed-integer representable cuts.…

Optimization and Control · Mathematics 2026-02-06 Akul Bansal , Simge Küçükyavuz

Injectivity is the defining property of a mapping that ensures no information is lost and any input can be perfectly reconstructed from its output. By performing hard thresholding, the ReLU function naturally interferes with this property,…

Machine Learning · Computer Science 2024-12-02 Daniel Haider , Martin Ehler , Peter Balazs

We give the first efficient algorithm for learning halfspaces in the testable learning model recently defined by Rubinfeld and Vasilyan (2023). In this model, a learner certifies that the accuracy of its output hypothesis is near optimal…

Machine Learning · Computer Science 2023-03-14 Aravind Gollakota , Adam R. Klivans , Konstantinos Stavropoulos , Arsen Vasilyan

The choice of activation functions in deep networks has a significant effect on the training dynamics and task performance. Currently, the most successful and widely-used activation function is the Rectified Linear Unit (ReLU). Although…

Neural and Evolutionary Computing · Computer Science 2017-10-30 Prajit Ramachandran , Barret Zoph , Quoc V. Le

We study the computation complexity of deep ReLU (Rectified Linear Unit) neural networks for the approximation of functions from the H\"older-Zygmund space of mixed smoothness defined on the $d$-dimensional unit cube when the dimension $d$…

Numerical Analysis · Mathematics 2021-07-26 Dinh Dũng , Van Kien Nguyen

We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss correction that are agnostic to both application domain and…

Machine Learning · Statistics 2017-03-23 Giorgio Patrini , Alessandro Rozza , Aditya Menon , Richard Nock , Lizhen Qu