English
Related papers

Related papers: Sharp Minima Can Generalize For Deep Nets

200 papers

The last decade has witnessed an experimental revolution in data science and machine learning, epitomised by deep learning methods. Indeed, many high-dimensional learning tasks previously thought to be beyond reach -- such as computer…

Machine Learning · Computer Science 2021-05-04 Michael M. Bronstein , Joan Bruna , Taco Cohen , Petar Veličković

Deep learning models have gained great popularity in statistical modeling because they lead to very competitive regression models, often outperforming classical statistical models such as generalized linear models. The disadvantage of deep…

Machine Learning · Computer Science 2021-07-26 Ronald Richman , Mario V. Wüthrich

The generalization error of deep neural networks via their classification margin is studied in this work. Our approach is based on the Jacobian matrix of a deep neural network and can be applied to networks with arbitrary non-linearities…

Machine Learning · Statistics 2017-07-04 Jure Sokolic , Raja Giryes , Guillermo Sapiro , Miguel R. D. Rodrigues

We consider deep linear networks with arbitrary convex differentiable loss. We provide a short and elementary proof of the fact that all local minima are global minima if the hidden layers are either 1) at least as wide as the input layer,…

Machine Learning · Computer Science 2018-07-25 Thomas Laurent , James von Brecht

Training neural networks means solving a high-dimensional optimization problem. Normally the goal is to minimize a loss function that depends on what is called the network function, or in other words the function that gives the network…

Machine Learning · Computer Science 2022-11-15 Umberto Michelucci

Deep nets generalize well despite having more parameters than the number of training samples. Recent works try to give an explanation using PAC-Bayes and Margin-based analyses, but do not as yet result in sample complexity bounds better…

Machine Learning · Computer Science 2018-11-28 Sanjeev Arora , Rong Ge , Behnam Neyshabur , Yi Zhang

In recent years, continual learning, a prediction setting in which the problem environment may evolve over time, has become an increasingly popular research field due to the framework's gearing towards complex, non-stationary objectives.…

Machine Learning · Computer Science 2024-09-27 Max Koster , Jude Kukla

In supervised learning, it is known that overparameterized neural networks with one hidden layer provably and efficiently learn and generalize, when trained using stochastic gradient descent with a sufficiently small learning rate and…

Machine Learning · Computer Science 2022-03-24 Kulin Shah , Amit Deshpande , Navin Goyal

In this paper, we analyze the effects of depth and width on the quality of local minima, without strong over-parameterization and simplification assumptions in the literature. Without any simplification assumption, for deep nonlinear neural…

Machine Learning · Computer Science 2019-07-10 Kenji Kawaguchi , Jiaoyang Huang , Leslie Pack Kaelbling

That shared features between train and test data are required for generalisation in artificial neural networks has been a common assumption of both proponents and critics of these models. Here, we show that convolutional architectures avoid…

Neural and Evolutionary Computing · Computer Science 2021-07-15 Jeff Mitchell , Jeffrey S. Bowers

Understanding the implicit regularization imposed by neural network architectures and gradient based optimization methods is a key challenge in deep learning and AI. In this work we provide sharp results for the implicit regularization…

Machine Learning · Computer Science 2023-07-17 Johan S. Wind , Vegard Antun , Anders C. Hansen

Modern deep learning models are over-parameterized, where different optima can result in widely varying generalization performance. The Sharpness-Aware Minimization (SAM) technique modifies the fundamental loss function that steers gradient…

Understanding the dynamics of optimization in deep learning is increasingly important as models scale. While stochastic gradient descent (SGD) and its variants reliably find solutions that generalize well, the mechanisms driving this…

Machine Learning · Computer Science 2026-04-07 Wei-Kai Chang , Rajiv Khanna

With a goal of understanding what drives generalization in deep networks, we consider several recently suggested explanations, including norm-based control, sharpness and robustness. We study how these measures can ensure generalization,…

Machine Learning · Computer Science 2017-07-07 Behnam Neyshabur , Srinadh Bhojanapalli , David McAllester , Nathan Srebro

Various iterative reconstruction algorithms for inverse problems can be unfolded as neural networks. Empirically, this approach has often led to improved results, but theoretical guarantees are still scarce. While some progress on…

Statistics Theory · Mathematics 2021-08-16 Arash Behboodi , Holger Rauhut , Ekkehard Schnoor

We prove that Riemannian contraction in a supervised learning setting implies generalization. Specifically, we show that if an optimizer is contracting in some Riemannian metric with rate $\lambda > 0$, it is uniformly algorithmically…

Machine Learning · Computer Science 2022-01-27 Leo Kozachkov , Patrick M. Wensing , Jean-Jacques Slotine

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

It has been argued in the past that high-dimensional neural networks do not exhibit local minima capable of trapping an optimisation algorithm. However, the relationship between loss surface modality and the neural architecture parameters,…

Machine Learning · Computer Science 2020-01-31 Anna Sergeevna Bosman , Andries Engelbrecht , Mardé Helbig

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge

Recent studies on deep neural networks show that flat minima of the loss landscape correlate with improved generalization. Sharpness-aware minimization (SAM) efficiently finds flat regions by updating the parameters according to the…

Machine Learning · Computer Science 2025-02-13 Albert Kjøller Jacobsen , Georgios Arvanitidis