English
Related papers

Related papers: On progressive sharpening, flat minima and general…

200 papers

Hessian based measures of flatness, such as the trace, Frobenius and spectral norms, have been argued, used and shown to relate to generalisation. In this paper we demonstrate that for feed forward neural networks under the cross entropy…

Machine Learning · Statistics 2020-06-17 Diego Granziol

Powerful deep neural networks are vulnerable to adversarial attacks. To obtain adversarially robust models, researchers have separately developed adversarial training and Jacobian regularization techniques. There are abundant theoretical…

Machine Learning · Statistics 2024-12-18 Dongya Wu , Xin Li

The correlation between the sharpness of loss minima and generalisation in the context of deep neural networks has been subject to discussion for a long time. Whilst mostly investigated in the context of selected benchmark data sets in the…

Classical analyses of gradient descent (GD) define a stability threshold based on the largest eigenvalue of the loss Hessian, often termed sharpness. When the learning rate lies below this threshold, training is stable and the loss…

Machine Learning · Computer Science 2025-11-18 Lawrence Wang , Stephen J. Roberts

The mechanisms by which certain training interventions, such as increasing learning rates and applying batch normalization, improve the generalization of deep networks remains a mystery. Prior works have speculated that "flatter" solutions…

Machine Learning · Computer Science 2023-05-25 Simran Kaur , Jeremy Cohen , Zachary C. Lipton

Information-theoretic (IT) generalization bounds have been used to study the generalization of learning algorithms. These bounds are intrinsically data- and algorithm-dependent so that one can exploit the properties of data and algorithm to…

Machine Learning · Computer Science 2026-01-06 Ze Peng , Jian Zhang , Yisen Wang , Lei Qi , Yinghuan Shi , Yang Gao

Deep learning has achieved remarkable success across a wide range of tasks, but its models often suffer from instability and vulnerability: small changes to the input may drastically affect predictions, while optimization can be hindered by…

Machine Learning · Computer Science 2025-10-30 Blaise Delattre

Modern machine learning applications have witnessed the remarkable success of optimization algorithms that are designed to find flat minima. Motivated by this design choice, we undertake a formal study that (i) formulates the notion of flat…

Machine Learning · Computer Science 2024-05-28 Kwangjun Ahn , Ali Jadbabaie , Suvrit Sra

There are various inverse problems -- including reconstruction problems arising in medical imaging -- where one is often aware of the forward operator that maps variables of interest to the observations. It is therefore natural to ask…

Image and Video Processing · Electrical Eng. & Systems 2020-06-23 Jaweria Amjad , Zhaoyan Lyu , Miguel R. D. Rodrigues

This article provides a comprehensive understanding of optimization in deep learning, with a primary focus on the challenges of gradient vanishing and gradient exploding, which normally lead to diminished model representational ability and…

Machine Learning · Computer Science 2023-11-14 Xianbiao Qi , Jianan Wang , Lei Zhang

Despite its empirical success, deep learning still lacks a comprehensive theoretical understanding of model fitting and generalization. This paper proposes the probability distribution (PD) learning framework to analyze the optimization and…

Machine Learning · Computer Science 2025-10-09 Binchuan Qi , Wei Gong , Li Li

Robustness of deep neural networks to input noise remains a critical challenge, as naive noise injection often degrades accuracy on clean (uncorrupted) data. We propose a novel training framework that addresses this trade-off through two…

Machine Learning · Statistics 2026-01-06 Hai-Vy Nguyen , Fabrice Gamboa , Sixin Zhang , Reda Chhaibi , Serge Gratton , Thierry Giaccone

Flat minima, known to enhance generalization and robustness in supervised learning, remain largely unexplored in generative models. In this work, we systematically investigate the role of loss surface flatness in generative models, both…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Taehwan Lee , Kyeongkook Seo , Jaejun Yoo , Sung Whan Yoon

Understanding the generalization behavior of learning algorithms is a central goal of learning theory. A recently emerging explanation is that learning algorithms are successful in practice because they converge to flat minima, which have…

Machine Learning · Computer Science 2026-05-26 Matan Schliserman , Shira Vansover-Hager , Tomer Koren

Understanding the geometry of the loss landscape near a minimum is key to explaining the implicit bias of gradient-based methods in non-convex optimization problems such as deep neural network training and deep matrix factorization. A…

Machine Learning · Statistics 2026-02-05 Anil Kamber , Rahul Parhi

Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from standard training, whereas understanding the geometric…

Machine Learning · Computer Science 2023-06-12 Jinseong Park , Hoki Kim , Yujin Choi , Jaewook Lee

Flatness of the loss curve around a model at hand has been shown to empirically correlate with its generalization ability. Optimizing for flatness has been proposed as early as 1994 by Hochreiter and Schmidthuber, and was followed by more…

Machine Learning · Computer Science 2023-07-06 Linara Adilova , Amr Abourayya , Jianning Li , Amin Dada , Henning Petzka , Jan Egger , Jens Kleesiek , Michael Kamp

The generalization performance of deep neural networks in classification tasks is a major concern in machine learning research. Despite widespread techniques used to diminish the over-fitting issue such as data augmentation,…

Machine Learning · Computer Science 2024-03-14 Mohammad Lashkari , Amin Gheibi

Modern neural network architectures often generalize well despite containing many more parameters than the size of the training dataset. This paper explores the generalization capabilities of neural networks trained via gradient descent. We…

Machine Learning · Computer Science 2019-07-05 Samet Oymak , Zalan Fabian , Mingchen Li , Mahdi Soltanolkotabi

During neural network training, the sharpness of the Hessian matrix of the training loss rises until training is on the edge of stability. As a result, even nonstochastic gradient descent does not accurately model the underlying dynamical…

Machine Learning · Statistics 2024-06-04 Mark Lowell , Catharine Kastner