English
Related papers

Related papers: Understanding the Loss Surface of Neural Networks …

200 papers

We propose a hierarchical training algorithm for standard feed-forward neural networks that adaptively extends the network architecture as soon as the optimization reaches a stationary point. By solving small (low-dimensional) optimization…

Numerical Analysis · Mathematics 2024-10-31 Michael Feischl , Alexander Rieder , Fabian Zehetgruber

The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting. We propose a unified optimization framework for…

Machine Learning · Computer Science 2018-05-24 Hadi Ghauch , Hossein Shokri-Ghadikolaei , Carlo Fischione , Mikael Skoglund

We analyze speed of convergence to global optimum for gradient descent training a deep linear neural network (parameterized as $x \mapsto W_N W_{N-1} \cdots W_1 x$) by minimizing the $\ell_2$ loss over whitened data. Convergence at a linear…

Machine Learning · Computer Science 2019-10-29 Sanjeev Arora , Nadav Cohen , Noah Golowich , Wei Hu

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

Binary classification is one of the most common problem in machine learning. It consists in predicting whether a given element belongs to a particular class. In this paper, a new algorithm for binary classification is proposed using a…

Machine Learning · Computer Science 2019-03-12 Alexandre Quemy

We prove that if an activation function satisfies some mild conditions and number of neurons in a two-layered fully connected neural network with this activation function is beyond a certain threshold, then gradient descent on quadratic…

Optimization and Control · Mathematics 2019-11-14 Biswarup Das , Eugene. A. Golikov

This work presents an algorithm for training Neural Networks where the loss function can be decomposed into two non-negative terms to be minimized. The proposed method is an adaptation of Inexact Restoration algorithms, constituting a…

Optimization and Control · Mathematics 2024-09-12 Dimary Moreno López

The implicit bias induced by the training of neural networks has become a topic of rigorous study. In the limit of gradient flow and gradient descent with appropriate step size, it has been shown that when one trains a deep linear network…

Machine Learning · Computer Science 2022-04-27 Thien Le , Stefanie Jegelka

We prove that, for the fundamental regression task of learning a single neuron, training a one-hidden layer ReLU network of any width by gradient flow from a small initialisation converges to zero loss and is implicitly biased to minimise…

Machine Learning · Computer Science 2023-10-03 Dmitry Chistikov , Matthias Englert , Ranko Lazic

The commitment to single-precision floating-point arithmetic is widespread in the deep learning community. To evaluate whether this commitment is justified, the influence of computing precision (single and double precision) on the…

Machine Learning · Computer Science 2022-11-01 Tomas Hrycej , Bernhard Bermeitinger , Siegfried Handschuh

We study the error landscape of deep linear and nonlinear neural networks with the squared error loss. Minimizing the loss of a deep linear neural network is a nonconvex problem, and despite recent progress, our understanding of this loss…

Machine Learning · Computer Science 2018-03-28 Chulhee Yun , Suvrit Sra , Ali Jadbabaie

Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications. Many recent works have been proposed to mitigate this issue, but…

Machine Learning · Computer Science 2020-08-14 Jooyoung Moon , Jihyo Kim , Younghak Shin , Sangheum Hwang

We study the training dynamics of shallow neural networks, in a two-timescale regime in which the stepsizes for the inner layer are much smaller than those for the outer layer. In this regime, we prove convergence of the gradient flow to a…

Optimization and Control · Mathematics 2023-10-26 Pierre Marion , Raphaël Berthier

Proper regularization is critical for speeding up training, improving generalization performance, and learning compact models that are cost efficient. We propose and analyze regularized gradient descent algorithms for learning shallow…

Machine Learning · Computer Science 2018-06-08 Samet Oymak

Understanding and controlling the informational complexity of neural networks is a central challenge in machine learning, with implications for generalization, optimization, and model capacity. While most approaches rely on entropy-based…

Debiased machine learning is a meta algorithm based on bias correction and sample splitting to calculate confidence intervals for functionals, i.e. scalar summaries, of machine learning algorithms. For example, an analyst may desire the…

Machine Learning · Statistics 2022-10-25 Victor Chernozhukov , Whitney K. Newey , Rahul Singh

We study the convergence properties of gradient descent for training deep linear neural networks, i.e., deep matrix factorizations, by extending a previous analysis for the related gradient flow. We show that under suitable conditions on…

Machine Learning · Computer Science 2021-11-25 Gabin Maxime Nguegnang , Holger Rauhut , Ulrich Terstiege

This paper introduces a new loss function, OSM (One-Sided Margin), to solve maximum-margin classification problems effectively. Unlike the hinge loss, in OSM the margin is explicitly determined with corresponding hyperparameters and then…

Machine Learning · Computer Science 2022-06-03 Ali Karimi , Zahra Mousavi Kouzehkanan , Reshad Hosseini , Hadi Asheri

Learning to rank has recently emerged as an attractive technique to train deep convolutional neural networks for various computer vision tasks. Pairwise ranking, in particular, has been successful in multi-label image classification,…

Computer Vision and Pattern Recognition · Computer Science 2017-06-02 Yuncheng Li , Yale Song , Jiebo Luo

In domains like bioinformatics, information retrieval and social network analysis, one can find learning tasks where the goal consists of inferring a ranking of objects, conditioned on a particular target object. We present a general kernel…

Machine Learning · Computer Science 2013-06-11 Tapio Pahikkala , Antti Airola , Michiel Stock , Bernard De Baets , Willem Waegeman