paper-with-me

홈 › Papers

Time/Accuracy Tradeoffs for Learning a ReLU with respect to Gaussian Marginals

2019-11-04 · NeurIPS 2019 12 · Surbhi Goel, Sushrut Karmalkar, Adam Klivans

We consider the problem of computing the best-fitting ReLU with respect to square-loss on a training set when the examples have been drawn according to a spherical Gaussian distribution (the labels can be arbitrary). Let $\mathsf{opt} < 1$ be the population loss of the best-fitting ReLU. We prove: 1. Finding a ReLU with square-loss $\mathsf{opt} + \epsilon$ is as hard as the problem of learning sparse parities with noise, widely thought to be computationally intractable. This is the first hardness result for learning a ReLU with respect to Gaussian marginals, and our results imply -{\emph unconditionally}- that gradient descent cannot converge to the global minimum in polynomial time. 2. There exists an efficient approximation algorithm for finding the best-fitting ReLU that achieves error $O(\mathsf{opt}^{2/3})$. The algorithm uses a novel reduction to noisy halfspace learning with respect to $0/1$ loss. Prior work due to Soltanolkotabi [Sol17] showed that gradient descent can find the best-fitting ReLU with respect to Gaussian marginals, if the training set is exactly labeled by a ReLU.

📄 PDF Abstract BibTeX arXiv:1911.01462

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

Smooth activations and reproducibility in deep networks

2020-10-20 · Gil I. Shamir, Dong Lin, Lorenzo Coviello

Deep networks are gradually penetrating almost every domain in our lives due to their amazing success. However, with substantive performance accuracy improvements comes the price of \emph{irreproducibility}. Two identica…

The Median is Easier than it Looks: Approximation with a Constant-Depth, Linear-Width ReLU Network

2026-02-06 · Abhigyan Dutta, Itay Safran, Paul Valiant arxiv

We study the approximation of the median of $d$ inputs using ReLU neural networks. We present depth-width tradeoffs under several settings, culminating in a constant-depth, linear-width construction that achieves exponen…

Large-width asymptotics for ReLU neural networks with $α$-Stable initializations

2022-06-16 · Stefano Favaro, Sandra Fortini, Stefano Peluchetti

There is a recent and growing literature on large-width asymptotic properties of Gaussian neural networks (NNs), namely NNs whose weights are initialized as Gaussian distributions. Two popular problems are: i) the study …

regression

DeepReDuce: ReLU Reduction for Fast Private Inference

2021-03-02 · Nandan Kumar Jha, Zahra Ghodsi, Siddharth Garg, Brandon Reagen

The recent rise of privacy concerns has led researchers to devise methods for private neural inference -- where inferences are made directly on encrypted data, never seeing inputs. The primary challenge facing private in…

N-ReLU: Zero-Mean Stochastic Extension of ReLU

2025-11-10 · Md Motaleb Hossen Manik, Md Zabirul Islam, Ge Wang arxiv

Activation functions are fundamental for enabling nonlinear representations in deep neural networks. However, the standard rectified linear unit (ReLU) often suffers from inactive or "dead" neurons caused by its hard zer…