English
Related papers

Related papers: Optimal Nonlinearities Improve Generalization Perf…

200 papers

We study generalization properties of random features (RF) regression in high dimensions optimized by stochastic gradient descent (SGD) in under-/over-parameterized regime. In this work, we derive precise non-asymptotic error bounds of RF…

Machine Learning · Statistics 2022-10-18 Fanghui Liu , Johan A. K. Suykens , Volkan Cevher

Gaussian Mixture Models (GMMs) range among the most frequently used models in machine learning. However, training large, general GMMs becomes computationally prohibitive for datasets that have many data points $N$ of high-dimensionality…

Machine Learning · Statistics 2025-12-12 Sebastian Salwig , Till Kahlke , Florian Hirschberger , Dennis Forster , Jörg Lücke

We present a new strategy for learning the functional relation between a pair of variables, while addressing inhomogeneities in the correlation structure of the available data, by modelling the sought function as a sample function of a…

Machine Learning · Statistics 2024-04-22 Gargi Roy , Dalia Chakrabarty

We present a general framework for solving a large class of learning problems with non-linear functions of classification rates. This includes problems where one wishes to optimize a non-decomposable performance metric such as the F-measure…

Machine Learning · Computer Science 2019-09-09 Harikrishna Narasimhan , Andrew Cotter , Maya Gupta

Distributed learning provides an attractive framework for scaling the learning task by sharing the computational load over multiple nodes in a network. Here, we investigate the performance of distributed learning for large-scale linear…

Machine Learning · Statistics 2021-11-03 Martin Hellkvist , Ayça Özçelikkale , Anders Ahlén

Bayesian optimization is an effective methodology for the global optimization of functions with expensive evaluations. It relies on querying a distribution over functions defined by a relatively cheap surrogate model. An accurate model for…

We analyse and explain the increased generalisation performance of iterate averaging using a Gaussian process perturbation model between the true and batch risk surface on the high dimensional quadratic. We derive three phenomena…

Machine Learning · Statistics 2021-11-02 Diego Granziol , Xingchen Wan , Samuel Albanie , Stephen Roberts

Gaussian processes (GPs) are the main surrogate functions used for sequential modelling such as Bayesian Optimization and Active Learning. Their drawbacks are poor scaling with data and the need to run an optimization loop when using a…

Machine Learning · Computer Science 2022-11-03 Paul E. Chang , Prakhar Verma , ST John , Victor Picheny , Henry Moss , Arno Solin

Multi--task learning seeks to improve the generalization error by leveraging the common information shared by multiple related tasks. One challenge in multi--task learning is identifying formulations capable of uncovering the common…

Machine Learning · Computer Science 2026-03-06 Ayed M. Alrashdi , Oussama Dhifallah , Houssem Sifaou

Near an optimal learning point of a neural network, the learning performance of gradient descent dynamics is dictated by the Hessian matrix of the loss function with respect to the network parameters. We characterize the Hessian…

Machine Learning · Statistics 2025-12-18 Carlos Couto , José Mourão , Mário A. T. Figueiredo , Pedro Ribeiro

Neural networks are universal function approximators which are known to generalize well despite being dramatically overparameterized. We study this phenomenon from the point of view of the spectral bias of neural networks. Our contributions…

Machine Learning · Computer Science 2022-09-07 Qingguo Hong , Jonathan W. Siegel , Qinyang Tan , Jinchao Xu

This document proposes a parametric activation function (ac.f.) aimed at improving multidimensional nonlinear data regression. It is a established knowledge that nonlinear ac.f's are required for learning nonlinear datasets. This work shows…

Machine Learning · Computer Science 2025-10-03 Enda D. V. Bigarella

A linear functional of an object from a convex symmetric set can be optimally estimated, in a worst-case sense, by a linear functional of observations made on the object. This well-known fact is extended here to a nonlinear setting: other…

Functional Analysis · Mathematics 2025-12-25 Simon Foucart

We propose an algorithm to actively estimate the parameters of a linear dynamical system. Given complete control over the system's input, our algorithm adaptively chooses the inputs to accelerate estimation. We show a finite time bound…

Machine Learning · Computer Science 2020-06-23 Andrew Wagenmaker , Kevin Jamieson

Linear models have shown great effectiveness and flexibility in many fields such as machine learning, signal processing and statistics. They can represent rich spaces of functions while preserving the convexity of the optimization problems…

Machine Learning · Computer Science 2020-07-09 Ulysse Marteau-Ferey , Francis Bach , Alessandro Rudi

Nonparametric extension of tensor regression is proposed. Nonlinearity in a high-dimensional tensor space is broken into simple local functions by incorporating low-rank tensor decomposition. Compared to naive nonparametric approaches, our…

Machine Learning · Statistics 2016-03-09 Masaaki Imaizumi , Kohei Hayashi

This article describes a multivariate polynomial regression method where the uncertainty of the input parameters are approximated with Gaussian distributions, derived from the central limit theorem for large weighted sums, directly from the…

Machine Learning · Statistics 2013-10-04 Peter Kovesarki , Ian C. Brock

We consider functions from the real numbers to the real numbers, output by a neural network with 1 hidden activation layer, arbitrary width, and ReLU activation function. We assume that the parameters of the neural network are chosen…

Machine Learning · Computer Science 2023-04-20 David Holmes

Sub-sampling is a common and often effective method to deal with the computational challenges of large datasets. However, for most statistical models, there is no well-motivated approach for drawing a non-uniform subsample. We show that the…

Machine Learning · Statistics 2017-09-07 Daniel Ting , Eric Brochu

Activation functions influence behavior and performance of DNNs. Nonlinear activation functions, like Rectified Linear Units (ReLU), Exponential Linear Units (ELU) and Scaled Exponential Linear Units (SELU), outperform the linear…

Neural and Evolutionary Computing · Computer Science 2019-02-05 Alberto Marchisio , Muhammad Abdullah Hanif , Semeen Rehman , Maurizio Martina , Muhammad Shafique