English
Related papers

Related papers: Sharp Minima Can Generalize: A Loss Landscape Pers…

200 papers

A machine learning (ML) system must learn not only to match the output of a target function on a training set, but also to generalize to novel situations in order to yield accurate predictions at deployment. In most practical applications,…

Machine Learning · Computer Science 2022-12-13 Clare Lyle

A leading hypothesis for the surprising generalization of neural networks is that the dynamics of gradient descent bias the model towards simple solutions, by searching through the solution space in an incremental order of complexity. We…

Machine Learning · Computer Science 2020-01-01 Daniel Gissin , Shai Shalev-Shwartz , Amit Daniely

For classification tasks, the performance of a deep neural network is determined by the structure of its decision boundary, whose geometry directly affects essential properties of the model, including accuracy and robustness. Motivated by a…

Machine Learning · Computer Science 2026-03-17 Matthew Burfitt , Jacek Brodzki , Pawel Dłotko

We present a new approach to understanding the relationship between loss curvature and input-output model behaviour in deep learning. Specifically, we use existing empirical analyses of the spectrum of deep network loss Hessians to ground…

Machine Learning · Computer Science 2023-09-28 Lachlan Ewen MacDonald , Jack Valmadre , Simon Lucey

In Theory IIb we characterize with a mix of theory and experiments the optimization of deep convolutional networks by Stochastic Gradient Descent. The main new result in this paper is theoretical and experimental evidence for the following…

Machine Learning · Computer Science 2018-01-09 Chiyuan Zhang , Qianli Liao , Alexander Rakhlin , Brando Miranda , Noah Golowich , Tomaso Poggio

A major challenge in understanding the generalization of deep learning is to explain why (stochastic) gradient descent can exploit the network architecture to find solutions that have good generalization performance when using high capacity…

Machine Learning · Computer Science 2019-02-12 Yifan Wu , Barnabas Poczos , Aarti Singh

The success of deep learning in high-dimensional settings is often attributed to the presence of low-dimensional structure in real-world data. While standard theoretical models typically assume that this structure lies in the target…

Machine Learning · Computer Science 2026-05-15 Elisabetta Cornacchia , Laurent Massoulié

Overparameterized deep networks that generalize well have been key to the dramatic success of deep learning in recent years. The reasons for their remarkable ability to generalize are not well understood yet. When class labels in the…

Machine Learning · Computer Science 2026-02-03 Simran Ketha , Venkatakrishnan Ramaswamy

We study the population loss landscape of two-layer ReLU networks of the form $\sum_{k=1}^K \mathrm{ReLU}(w_k^\top x)$ in a realisable teacher-student setting with Gaussian covariates. We show that local minima admit an exact…

Machine Learning · Statistics 2026-04-13 Jie Huang , Bruno Loureiro , Stefano Sarao Mannelli

Traditional landscape analysis of deep neural networks aims to show that no sub-optimal local minima exist in some appropriate sense. From this, one may be tempted to conclude that descent algorithms which escape saddle points will reach a…

Machine Learning · Computer Science 2020-01-01 Shiyu Liang , Ruoyu Sun , R. Srikant

Deep learning researchers commonly suggest that converged models are stuck in local minima. More recently, some researchers observed that under reasonable assumptions, the vast majority of critical points are saddle points, not true minima.…

Machine Learning · Computer Science 2016-02-25 Zachary C. Lipton

Deep learning have achieved promising results on a wide spectrum of AI applications. Larger datasets and models consistently yield better performance. However, we generally spend longer training time on more computation and communication.…

Machine Learning · Computer Science 2021-11-03 Xiaoxin He , Fuzhao Xue , Xiaozhe Ren , Yang You

An open problem in machine learning is whether flat minima generalize better and how to compute such minima efficiently. This is a very challenging problem. As a first step towards understanding this question we formalize it as an…

Machine Learning · Statistics 2019-05-13 Nikolas Kantas , Panos Parpas , Grigorios A. Pavliotis

Neural network training relies on our ability to find "good" minimizers of highly non-convex loss functions. It is well-known that certain network architecture designs (e.g., skip connections) produce loss functions that train easier, and…

Machine Learning · Computer Science 2018-11-08 Hao Li , Zheng Xu , Gavin Taylor , Christoph Studer , Tom Goldstein

It is widely believed that natural image data exhibits low-dimensional structure despite the high dimensionality of conventional pixel representations. This idea underlies a common intuition for the remarkable success of deep learning in…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Phillip Pope , Chen Zhu , Ahmed Abdelkader , Micah Goldblum , Tom Goldstein

The growth and success of deep learning approaches can be attributed to two major factors: availability of hardware resources and availability of large number of training samples. For problems with large training databases, deep learning…

Computer Vision and Pattern Recognition · Computer Science 2020-08-11 Rohit Keshari , Soumyadeep Ghosh , Saheb Chhabra , Mayank Vatsa , Richa Singh

In this paper, we hypothesize that internal function sharing is one of the reasons to weaken o.o.d. or systematic generalization in deep learning for classification tasks. Under equivalent prediction, a model partitions an input space into…

Machine Learning · Computer Science 2022-08-25 Yuanpeng Li

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

Traditional deep learning algorithms often fail to generalize when they are tested outside of the domain of the training data. The issue can be mitigated by using unlabeled data from the target domain at training time, but because data…

Computer Vision and Pattern Recognition · Computer Science 2023-02-03 Thomas Duboudin , Emmanuel Dellandréa , Corentin Abgrall , Gilles Hénaff , Liming Chen

Deep learning (DL) creates impactful advances following a virtuous recipe: model architecture search, creating large training data sets, and scaling computation. It is widely believed that growing training sets and models should improve…

‹ Prev 1 3 4 5 6 7 10 Next ›