English
Related papers

Related papers: The Geometric Occam's Razor Implicit in Deep Learn…

200 papers

We take a geometrical viewpoint and present a unifying view on supervised deep learning with the Bregman divergence loss function - this entails frequent classification and prediction tasks. Motivated by simulations we suggest that there is…

Machine Learning · Computer Science 2021-07-07 Petr Taborsky , Lars Kai Hansen

Understanding the operation of biological and artificial networks remains a difficult and important challenge. To identify general principles, researchers are increasingly interested in surveying large collections of networks that are…

Machine Learning · Statistics 2022-01-14 Alex H. Williams , Erin Kunz , Simon Kornblith , Scott W. Linderman

Linear programming has played a crucial role in shaping decision-making, resource allocation, and cost reduction in various domains. In this paper, we investigate the application of overparametrized neural networks and their implicit bias…

Optimization and Control · Mathematics 2023-10-05 Haoyue Wang , Promit Ghosal , Rahul Mazumder

In this paper, we evaluate the accuracy of deep learning approaches on geospatial vector geometry classification tasks. The purpose of this evaluation is to investigate the ability of deep learning models to learn from geometry coordinates…

Machine Learning · Statistics 2019-06-12 Rein van 't Veer , Peter Bloem , Erwin Folmer

Deep learning has shown strong potential for scientific discovery, but its ability to model macroscopic rigid-body kinematic constraints remains underexplored. We study this problem on spatial over-constrained mechanisms and propose…

Robotics · Computer Science 2026-04-03 Haoyu Sun , Meng Zhao , Tianhao Wang , Jianxu Wu

Difficulties in replication and reproducibility of empirical evidences in machine learning research have become a prominent topic in recent years. Ensuring that machine learning research results are sound and reliable requires…

Machine Learning · Computer Science 2024-03-20 Tobias Hille , Maximilian Stubbemann , Tom Hanika

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 a convex analytic approach to analyze finite width two-layer ReLU networks. We first prove that an optimal solution to the regularized training problem can be characterized as extreme points of a convex set, where simple…

Machine Learning · Computer Science 2021-09-01 Tolga Ergen , Mert Pilanci

Understanding the asymptotic behavior of gradient-descent training of deep neural networks is essential for revealing inductive biases and improving network performance. We derive the infinite-time training limit of a mathematically…

Machine Learning · Statistics 2022-02-08 Samuel Lippl , L. F. Abbott , SueYeon Chung

Overparameterized ML models, including neural networks, typically induce underdetermined training objectives with multiple global minima. The implicit bias refers to the limiting global minimum that is attained by a common optimization…

Machine Learning · Statistics 2026-03-06 Kuo-Wei Lai , Guanghui Wang , Molei Tao , Vidya Muthukumar

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

Based on the tree architecture, the objective of this paper is to design deep neural networks with two or more hidden layers (called deep nets) for realization of radial functions so as to enable rotational invariance for near-optimal…

Machine Learning · Computer Science 2019-04-04 Charles K. Chui , Shao-Bo Lin , Ding-Xuan Zhou

We study the generalization of deep learning models in relation to the convex hull of their training sets. A trained image classifier basically partitions its domain via decision boundaries and assigns a class to each of those partitions.…

Machine Learning · Computer Science 2021-01-26 Roozbeh Yousefzadeh

Implicit Graph Neural Networks (GNNs) have achieved significant success in addressing graph learning problems recently. However, poorly designed implicit GNN layers may have limited adaptability to learn graph metrics, experience…

Machine Learning · Computer Science 2024-02-16 Guoji Fu , Mohammed Haroon Dupty , Yanfei Dong , Lee Wee Sun

Deep learning and convolutional neural networks in particular are powerful and promising tools for cosmological analysis of large-scale structure surveys. They are already providing similar performance to classical analysis methods using…

Cosmology and Nongalactic Astrophysics · Physics 2026-05-06 Gaspard Aymerich , Tomasz Kacprzak , Alexandre Refregier

Deep neural networks are often trained in the over-parametrized regime (i.e. with far more parameters than training examples), and understanding why the training converges to solutions that generalize remains an open problem. Several…

Machine Learning · Statistics 2018-03-23 Hartmut Maennel , Olivier Bousquet , Sylvain Gelly

Many machine/deep learning artificial neural networks are trained to simply be interpolation functions that map input variables to output values interpolated from the training data in a linear/nonlinear fashion. Even when the input/output…

Computational Physics · Physics 2020-03-18 Zhenglin Geng , Dan Johnson , Ronald Fedkiw

Deep learning algorithms demonstrate a surprising ability to learn high-dimensional tasks from limited examples. This is commonly attributed to the depth of neural networks, enabling them to build a hierarchy of abstract, low-dimensional…

Machine Learning · Computer Science 2024-07-04 Francesco Cagnetta , Leonardo Petrini , Umberto M. Tomasini , Alessandro Favero , Matthieu Wyart

We consider training over-parameterized two-layer neural networks with Rectified Linear Unit (ReLU) using gradient descent (GD) method. Inspired by a recent line of work, we study the evolutions of network prediction errors across GD…

Machine Learning · Computer Science 2019-09-04 Lili Su , Pengkun Yang

Solomonoff's general theory of inference and the Minimum Description Length principle formalize Occam's razor, and hold that a good model of data is a model that is good at losslessly compressing the data, including the cost of describing…

Machine Learning · Computer Science 2019-01-29 Léonard Blier , Yann Ollivier