English
Related papers

Related papers: Exact Gaussian Moment Matching for Residual Networ…

200 papers

We derive an asymptotic expansion for the log likelihood of Gaussian mixture models (GMMs) with equal covariance matrices in the low signal-to-noise regime. The expansion reveals an intimate connection between two types of algorithms for…

Statistics Theory · Mathematics 2020-06-30 Anya Katsevich , Afonso Bandeira

We propose practical deep Gaussian process models on Riemannian manifolds, similar in spirit to residual neural networks. With manifold-to-manifold hidden layers and an arbitrary last layer, they can model manifold- and scalar-valued…

Machine Learning · Statistics 2025-03-03 Kacper Wyrwal , Andreas Krause , Viacheslav Borovitskiy

In this paper, we seek to tackle a challenge in training low-precision networks: the notorious difficulty in propagating gradient through a low-precision network due to the non-differentiable quantization function. We propose a solution by…

Computer Vision and Pattern Recognition · Computer Science 2020-03-19 Bohan Zhuang , Lingqiao Liu , Mingkui Tan , Chunhua Shen , Ian Reid

Understanding the impact of data structure on the computational tractability of learning is a key challenge for the theory of neural networks. Many theoretical works do not explicitly model training data, or assume that inputs are drawn…

Machine Learning · Statistics 2022-05-23 Sebastian Goldt , Bruno Loureiro , Galen Reeves , Florent Krzakala , Marc Mézard , Lenka Zdeborová

Distributed optimization is widely used in large-scale and privacy-preserving machine learning, where each agent stores a local objective and communicates only with its neighbors in a connected network. We study decentralized second-order…

In this paper, we compare the performance of two methods for estimating Bayesian networks from data containing exogenous variables and random effects. The first method is fully Bayesian in which a prior distribution is placed on the…

Methodology · Statistics 2011-12-02 Jessica Kasza , Patty Solomon

We study the use of Gaussian process emulators to approximate the parameter-to-observation map or the negative log-likelihood in Bayesian inverse problems. We prove error bounds on the Hellinger distance between the true posterior…

Numerical Analysis · Mathematics 2024-10-01 Andrew M. Stuart , Aretha L. Teckentrup

We prove a large deviation principle for deep neural networks with Gaussian weights and at most linearly growing activation functions, such as ReLU. This generalises earlier work, in which bounded and continuous activation functions were…

Machine Learning · Statistics 2026-02-10 Quirin Vogel

Second-order methods are widely adopted to improve the convergence rate of learning algorithms. In federated learning (FL), these methods require the clients to share their local Hessian matrices with the parameter server (PS), which comes…

Machine Learning · Computer Science 2024-12-06 Shayan Mohajer Hamidi , Ali Bereyhi , Saba Asaad , H. Vincent Poor

We study the problem of PAC learning a linear combination of $k$ ReLU activations under the standard Gaussian distribution on $\mathbb{R}^d$ with respect to the square loss. Our main result is an efficient algorithm for this learning task…

Machine Learning · Computer Science 2023-07-26 Ilias Diakonikolas , Daniel M. Kane

Gaussian processes are distributions over functions that are versatile and mathematically convenient priors in Bayesian modelling. However, their use is often impeded for data with large numbers of observations, $N$, due to the cubic (in…

Machine Learning · Statistics 2020-08-04 David R. Burt , Carl Edward Rasmussen , Mark van der Wilk

We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. In contrast to weight or filter-level pruning, layer pruning reduces the harder to parallelize…

Machine Learning · Computer Science 2024-06-10 Valentin Frank Ingmar Guenter , Athanasios Sideris

We develop efficient algorithms for estimating low-degree moments of unknown distributions in the presence of adversarial outliers. The guarantees of our algorithms improve in many cases significantly over the best previous ones, obtained…

Data Structures and Algorithms · Computer Science 2017-12-27 Pravesh K. Kothari , David Steurer

Given any deep fully connected neural network, initialized with random Gaussian parameters, we bound from above the quadratic Wasserstein distance between its output distribution and a suitable Gaussian process. Our explicit inequalities…

Machine Learning · Computer Science 2023-09-25 Andrea Basteri , Dario Trevisan

The points of a moment variety are the vectors of all moments up to some order of a family of probability distributions. We study this variety for mixtures of Gaussians. Following up on Pearson's classical work from 1894, we apply current…

Algebraic Geometry · Mathematics 2017-04-06 Carlos Améndola , Jean-Charles Faugère , Bernd Sturmfels

Neural networks with REctified Linear Unit (ReLU) activation functions (a.k.a. ReLU networks) have achieved great empirical success in various domains. Nonetheless, existing results for learning ReLU networks either pose assumptions on the…

Machine Learning · Statistics 2019-05-01 Gang Wang , Georgios B. Giannakis , Jie Chen

We develop new uncertainty propagation methods for feed-forward neural network architectures with leaky ReLU activation functions subject to random perturbations in the input vectors. In particular, we derive analytical expressions for the…

Machine Learning · Computer Science 2025-08-12 Jeremy Diamzon , Daniele Venturi

In the classic measurement error framework, covariates are contaminated by independent additive noise. This paper considers parameter estimation in such a linear errors-in-variables model where the unknown measurement error distribution is…

Methodology · Statistics 2023-10-24 Linh H. Nghiem , Cornelis J. Potgieter

First order optimization algorithms play a major role in large scale machine learning. A new class of methods, called adaptive algorithms, were recently introduced to adjust iteratively the learning rate for each coordinate. Despite great…

Machine Learning · Computer Science 2019-10-01 André Belotto da Silva , Maxime Gazeau

We provide a new information-theoretic generalization error bound that is exactly tight (i.e., matching even the constant) for the canonical quadratic Gaussian (location) problem. Most existing bounds are order-wise loose in this setting,…

Information Theory · Computer Science 2023-11-14 Ruida Zhou , Chao Tian , Tie Liu
‹ Prev 1 8 9 10 Next ›