English
Related papers

Related papers: General Loss Functions Lead to (Approximate) Inter…

200 papers

We establish the asymptotic implicit bias of gradient descent (GD) for generic non-homogeneous deep networks under exponential loss. Specifically, we characterize three key properties of GD iterates starting from a sufficiently small…

Machine Learning · Computer Science 2025-07-17 Yuhang Cai , Kangjie Zhou , Jingfeng Wu , Song Mei , Michael Lindsey , Peter L. Bartlett

This paper presents GeNI-ADMM, a framework for large-scale composite convex optimization that facilitates theoretical analysis of both existing and new approximate ADMM schemes. GeNI-ADMM encompasses any ADMM algorithm that solves a first-…

Optimization and Control · Mathematics 2025-06-23 Zachary Frangella , Theo Diamandis , Bartolomeo Stellato , Madeleine Udell

A main puzzle of deep neural networks (DNNs) revolves around the apparent absence of "overfitting", defined in this paper as follows: the expected error does not get worse when increasing the number of neurons or of iterations of gradient…

Machine Learning · Computer Science 2018-07-02 Tomaso Poggio , Qianli Liao , Brando Miranda , Andrzej Banburski , Xavier Boix , Jack Hidary

We consider composite loss functions for multiclass prediction comprising a proper (i.e., Fisher-consistent) loss over probability distributions and an inverse link function. We establish conditions for their (strong) convexity and explore…

Machine Learning · Computer Science 2012-06-22 Mark Reid , Robert Williamson , Peng Sun

Convex optimizers have known many applications as differentiable layers within deep neural architectures. One application of these convex layers is to project points into a convex set. However, both forward and backward passes of these…

Machine Learning · Computer Science 2020-11-16 Riad Akrour , Asma Atamna , Jan Peters

A key idea in convex optimization theory is to use well-structured affine functions to approximate general functions, leading to impactful developments in conjugate functions and convex duality theory. This raises the question: what are the…

Optimization and Control · Mathematics 2025-04-22 Ningji Wei

We develop new approaches in multi-class settings for constructing proper scoring rules and hinge-like losses and establishing corresponding regret bounds with respect to the zero-one or cost-weighted classification loss. Our construction…

Statistics Theory · Mathematics 2021-05-18 Zhiqiang Tan , Xinwei Zhang

`Double descent' delineates the generalization behaviour of models depending on the regime they belong to: under- or over-parameterized. The current theoretical understanding behind the occurrence of this phenomenon is primarily based on…

Machine Learning · Statistics 2022-03-15 Sidak Pal Singh , Aurelien Lucchi , Thomas Hofmann , Bernhard Schölkopf

We consider a teacher-student model of supervised learning with a fully-trained two-layer neural network whose width $k$ and input dimension $d$ are large and proportional. We provide an effective theory for approximating the Bayes-optimal…

Machine Learning · Statistics 2025-04-02 Jean Barbier , Francesco Camilli , Minh-Toan Nguyen , Mauro Pastore , Rudy Skerk

The ability of overparameterized deep networks to interpolate noisy data, while at the same time showing good generalization performance, has been recently characterized in terms of the double descent curve for the test error. Common…

Machine Learning · Computer Science 2023-04-11 Matteo Gamba , Erik Englesson , Mårten Björkman , Hossein Azizpour

We formalize and study the natural approach of designing convex surrogate loss functions via embeddings, for problems such as classification, ranking, or structured prediction. In this approach, one embeds each of the finitely many…

Machine Learning · Computer Science 2022-06-30 Jessie Finocchiaro , Rafael M. Frongillo , Bo Waggoner

Efforts to understand the generalization mystery in deep learning have led to the belief that gradient-based optimization induces a form of implicit regularization, a bias towards models of low "complexity." We study the implicit…

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

In previous literature, backward error analysis was used to find ordinary differential equations (ODEs) approximating the gradient descent trajectory. It was found that finite step sizes implicitly regularize solutions because terms…

Machine Learning · Computer Science 2024-06-18 Matias D. Cattaneo , Jason M. Klusowski , Boris Shigida

We study the properties of alignment, a form of implicit regularization, in linear neural networks under gradient descent. We define alignment for fully connected networks with multidimensional outputs and show that it is a natural…

Machine Learning · Computer Science 2020-06-18 Adityanarayanan Radhakrishnan , Eshaan Nichani , Daniel Bernstein , Caroline Uhler

Qualification conditions (also termed constraint qualifications) help avoid pathological behavior at domain boundaries in convex analysis. By generalizing facial reduction from conic programming to general convex programs of the form $f(x)…

Optimization and Control · Mathematics 2026-02-11 Matthew S. Scott

Implicit regularization refers to the tendency of local search algorithms to converge to low-dimensional solutions, even when such structures are not explicitly enforced. Despite its ubiquity, the mechanism underlying this behavior remains…

Machine Learning · Computer Science 2025-12-10 Jianhao Ma , Geyu Liang , Salar Fattahi

Autoencoders, which consist of an encoder and a decoder, are widely used in machine learning for dimension reduction of high-dimensional data. The encoder embeds the input data manifold into a lower-dimensional latent space, while the…

Numerical Analysis · Mathematics 2024-03-29 Juliane Braunsmann , Marko Rajković , Martin Rumpf , Benedikt Wirth

In order to train networks for verified adversarial robustness, it is common to over-approximate the worst-case loss over perturbation regions, resulting in networks that attain verifiability at the expense of standard performance. As shown…

There has been a long history of works showing that neural networks have hard time extrapolating beyond the training set. A recent study by Balestriero et al. (2021) challenges this view: defining interpolation as the state of belonging to…

Machine Learning · Computer Science 2022-07-19 Laurent Bonnasse-Gahot

We consider the dynamics of gradient descent (GD) in overparameterized single hidden layer neural networks with a squared loss function. Recently, it has been shown that, under some conditions, the parameter values obtained using GD achieve…

Machine Learning · Computer Science 2021-05-17 Siddhartha Satpathi , R Srikant
‹ Prev 1 3 4 5 6 7 10 Next ›