English
Related papers

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

200 papers

Deep neural networks trained on a wide range of datasets demonstrate impressive transferability. Deep features appear general in that they are applicable to many datasets and tasks. Such property is in prevalent use in real-world…

Machine Learning · Computer Science 2019-09-27 Hong Liu , Mingsheng Long , Jianmin Wang , Michael I. Jordan

Current methods to interpret deep learning models by generating saliency maps generally rely on two key assumptions. First, they use first-order approximations of the loss function neglecting higher-order terms such as the loss curvatures.…

Machine Learning · Computer Science 2019-06-03 Sahil Singla , Eric Wallace , Shi Feng , Soheil Feizi

Sharpness-Aware Minimization (SAM) has substantially improved the generalization of neural networks under various settings. Despite the success, its effectiveness remains poorly understood. In this work, we discover an intriguing phenomenon…

Machine Learning · Computer Science 2025-02-21 Zhanpeng Zhou , Mingze Wang , Yuchen Mao , Bingrui Li , Junchi Yan

Lipschitz continuity is a crucial functional property of any predictive model, that naturally governs its robustness, generalisation, as well as adversarial vulnerability. Contrary to other works that focus on obtaining tighter bounds and…

Machine Learning · Computer Science 2024-05-16 Grigory Khromov , Sidak Pal Singh

We study centralized distributed data parallel training of deep neural networks (DNNs), aiming to improve the trade-off between communication efficiency and model performance of the local gradient methods. To this end, we revisit the…

Machine Learning · Computer Science 2025-10-13 Tolga Dimlioglu , Anna Choromanska

We establish a margin based data dependent generalization error bound for a general family of deep neural networks in terms of the depth and width, as well as the Jacobian of the networks. Through introducing a new characterization of the…

Machine Learning · Computer Science 2019-07-05 Xingguo Li , Junwei Lu , Zhaoran Wang , Jarvis Haupt , Tuo Zhao

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

Model compression by way of parameter pruning, quantization, or distillation has recently gained popularity as an approach for reducing the computational requirements of modern deep neural network models for NLP. Inspired by prior works…

Computation and Language · Computer Science 2023-10-10 Clara Na , Sanket Vaibhav Mehta , Emma Strubell

In this paper, we propose a geometric framework to analyze the convergence properties of gradient descent trajectories in the context of linear neural networks. We translate a well-known empirical observation of linear neural nets into a…

Machine Learning · Computer Science 2023-08-02 Yacine Chitour , Zhenyu Liao , Romain Couillet

The key distinguishing property of a Bayesian approach is marginalization, rather than using a single setting of weights. Bayesian marginalization can particularly improve the accuracy and calibration of modern deep neural networks, which…

Machine Learning · Computer Science 2022-03-31 Andrew Gordon Wilson , Pavel Izmailov

We prove linear convergence of gradient descent to a global optimum for the training of deep residual networks with constant layer width and smooth activation function. We show that if the trained weights, as a function of the layer index,…

Machine Learning · Computer Science 2023-01-26 Rama Cont , Alain Rossier , RenYuan Xu

It is important to understand how dropout, a popular regularization method, aids in achieving a good generalization solution during neural network training. In this work, we present a theoretical derivation of an implicit regularization of…

Machine Learning · Computer Science 2023-04-11 Zhongwang Zhang , Zhi-Qin John Xu

Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models. However, existing quantization methods suffer from accuracy degradation compared to full-precision (FP)…

Machine Learning · Computer Science 2022-10-14 Zheng Wang , Juncheng B Li , Shuhui Qu , Florian Metze , Emma Strubell

Modern machine learning usually involves predictors in the overparameterised setting (number of trained parameters greater than dataset size), and their training yields not only good performance on training data, but also good…

Machine Learning · Statistics 2025-02-12 Maxime Haddouche , Paul Viallard , Umut Simsekli , Benjamin Guedj

The optimization foundations of deep linear networks have recently received significant attention. However, due to their inherent non-convexity and hierarchical structure, analyzing the loss functions of deep linear networks remains a…

Optimization and Control · Mathematics 2025-09-24 Po Chen , Rujun Jiang , Peng Wang

The generalization performance of deep neural networks with regard to the optimization algorithm is one of the major concerns in machine learning. This performance can be affected by various factors. In this paper, we theoretically prove…

Machine Learning · Computer Science 2023-08-23 Mohammad Lashkari , Amin Gheibi

Deep Neural Networks (DNNs) generalization is known to be closely related to the flatness of minima, leading to the development of Sharpness-Aware Minimization (SAM) for seeking flatter minima and better generalization. In this paper, we…

Machine Learning · Computer Science 2024-12-06 Yun Yue , Jiadi Jiang , Zhiling Ye , Ning Gao , Yongchao Liu , Ke Zhang

It has been intensively investigated that the local shape, especially flatness, of the loss landscape near a minimum plays an important role for generalization of deep models. We developed a training algorithm called PoF: Post-Training of…

Machine Learning · Computer Science 2022-07-06 Ikuro Sato , Ryota Yamada , Masayuki Tanaka , Nakamasa Inoue , Rei Kawakami

Neural networks that land in flat regions of the loss landscape tend to generalise better than those in sharp regions. Sharpness-Aware Minimisation exploits this to improve generalisation. But function-preserving reparameterisation can…

Machine Learning · Computer Science 2026-05-08 Michael Timothy Bennett

Adversarial training (AT) has become the de-facto standard to obtain models robust against adversarial examples. However, AT exhibits severe robust overfitting: cross-entropy loss on adversarial examples, so-called robust loss, decreases…

Machine Learning · Computer Science 2021-10-07 David Stutz , Matthias Hein , Bernt Schiele