English
Related papers

Related papers: Deep Double Descent via Smooth Interpolation

200 papers

Deep neural networks trained on large supervised datasets have led to impressive results in image classification and other tasks. However, well-annotated datasets can be time-consuming and expensive to collect, lending increased interest to…

Machine Learning · Computer Science 2018-02-27 David Rolnick , Andreas Veit , Serge Belongie , Nir Shavit

In many modern applications of deep learning the neural network has many more parameters than the data points used for its training. Motivated by those practices, a large body of recent theoretical research has been devoted to studying…

Statistics Theory · Mathematics 2022-12-07 A. Tsigler , P. L. Bartlett

Overparametrized neural networks tend to perfectly fit noisy training data yet generalize well on test data. Inspired by this empirical observation, recent work has sought to understand this phenomenon of benign overfitting or harmless…

Machine Learning · Statistics 2022-02-23 Andrew D. McRae , Santhosh Karnik , Mark A. Davenport , Vidya Muthukumar

Monotonic linear interpolation (MLI) - on the line connecting a random initialization with the minimizer it converges to, the loss and accuracy are monotonic - is a phenomenon that is commonly observed in the training of neural networks.…

Machine Learning · Statistics 2023-02-15 Xiang Wang , Annie N. Wang , Mo Zhou , Rong Ge

A central question of machine learning is how deep nets manage to learn tasks in high dimensions. An appealing hypothesis is that they achieve this feat by building a representation of the data where information irrelevant to the task is…

Machine Learning · Computer Science 2022-11-24 Umberto M. Tomasini , Leonardo Petrini , Francesco Cagnetta , Matthieu Wyart

When using recurrent neural networks (RNNs) it is common practice to apply trained models to sequences longer than those seen in training. This "extrapolating" usage deviates from the traditional statistical learning setup where guarantees…

Machine Learning · Computer Science 2022-03-25 Edo Cohen-Karlik , Avichai Ben David , Nadav Cohen , Amir Globerson

In the context of neural network models, overparametrization refers to the phenomena whereby these models appear to generalize well on the unseen data, even though the number of parameters significantly exceeds the sample sizes, and the…

Machine Learning · Statistics 2020-03-25 Matt Emschwiller , David Gamarnik , Eren C. Kızıldağ , Ilias Zadik

Given two networks with the same training loss on a dataset, when would they have drastically different test losses and errors? Better understanding of this question of generalization may improve practical applications of deep networks. In…

Machine Learning · Computer Science 2018-07-26 Qianli Liao , Brando Miranda , Andrzej Banburski , Jack Hidary , Tomaso Poggio

In this paper, we investigate the extrapolation capabilities of implicit deep learning models in handling unobserved data, where traditional deep neural networks may falter. Implicit models, distinguished by their adaptability in layer…

Machine Learning · Computer Science 2024-07-22 Juliette Decugis , Alicia Y. Tsai , Max Emerling , Ashwin Ganesh , Laurent El Ghaoui

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

Machine Learning · Computer Science 2022-10-17 Lang Huang , Chao Zhang , Hongyang Zhang

Understanding the inductive bias and generalization properties of large overparametrized machine learning models requires to characterize the dynamics of the training algorithm. We study the learning dynamics of large two-layer neural…

Machine Learning · Statistics 2025-10-30 Andrea Montanari , Pierfrancesco Urbani

Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are limited in providing theoretical guarantees for the performance of the…

Machine Learning · Computer Science 2020-11-17 Baharan Mirzasoleiman , Kaidi Cao , Jure Leskovec

A recent line of research has highlighted the existence of a "double descent" phenomenon in deep learning, whereby increasing the number of training examples $N$ causes the generalization error of neural networks to peak when $N$ is of the…

Machine Learning · Computer Science 2022-01-12 Stéphane d'Ascoli , Levent Sagun , Giulio Biroli

Diffusion models have achieved remarkable progress in various domains with an intriguing ability to produce new data that do not exist in the training set. In this work, we study the hypothesis that such creativity arises from the neural…

Machine Learning · Computer Science 2026-04-21 Zhengdao Chen

Neural networks trained via gradient descent with random initialization and without any regularization enjoy good generalization performance in practice despite being highly overparametrized. A promising direction to explain this phenomenon…

Machine Learning · Computer Science 2022-05-17 Hancheng Min , Salma Tarmoun , Rene Vidal , Enrique Mallada

While deep learning is successful in a number of applications, it is not yet well understood theoretically. A satisfactory theoretical characterization of deep learning however, is beginning to emerge. It covers the following questions: 1)…

Machine Learning · Computer Science 2019-08-27 Tomaso Poggio , Andrzej Banburski , Qianli Liao

Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance trade-off in classical learning theory. Recent studies claimed…

Machine Learning · Computer Science 2022-11-15 Xiao Zhang , Haoyi Xiong , Dongrui Wu

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

Machine Learning · Computer Science 2024-08-12 Pietro Morerio , Ruggero Ragonesi , Vittorio Murino

Deep neural networks (DNNs) trained for image denoising are able to generate high-quality samples with score-based reverse diffusion algorithms. These impressive capabilities seem to imply an escape from the curse of dimensionality, but…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Zahra Kadkhodaie , Florentin Guth , Eero P. Simoncelli , Stéphane Mallat

Linear interpolation between initial neural network parameters and converged parameters after training with stochastic gradient descent (SGD) typically leads to a monotonic decrease in the training objective. This Monotonic Linear…

Machine Learning · Computer Science 2021-04-26 James Lucas , Juhan Bae , Michael R. Zhang , Stanislav Fort , Richard Zemel , Roger Grosse