English
Related papers

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

200 papers

Second-order methods for neural network optimization have several advantages over methods based on first-order gradient descent, including better scaling to large mini-batch sizes and fewer updates needed for convergence. But they are…

Machine Learning · Computer Science 2017-12-21 Huishuai Zhang , Caiming Xiong , James Bradbury , Richard Socher

We consider some supervised binary classification tasks and a regression task, whereas SVM and Deep Learning, at present, exhibit the best generalization performances. We extend the work [3] on a generalized quadratic loss for learning…

Machine Learning · Computer Science 2021-02-16 Filippo Portera

Recently, learning algorithms motivated from sharpness of loss surface as an effective measure of generalization gap have shown state-of-the-art performances. Nevertheless, sharpness defined in a rigid region with a fixed radius, has a…

Machine Learning · Computer Science 2021-06-30 Jungmin Kwon , Jeongseop Kim , Hyunseo Park , In Kwon Choi

Teacher-student models provide a framework in which the typical-case performance of high-dimensional supervised learning can be described in closed form. The assumptions of Gaussian i.i.d. input data underlying the canonical teacher-student…

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

We show that the input correlation matrix of typical classification datasets has an eigenspectrum where, after a sharp initial drop, a large number of small eigenvalues are distributed uniformly over an exponentially large range. This…

Machine Learning · Computer Science 2022-06-23 Rubing Yang , Jialin Mao , Pratik Chaudhari

We investigate the local spectral statistics of the loss surface Hessians of artificial neural networks, where we discover excellent agreement with Gaussian Orthogonal Ensemble statistics across several network architectures and datasets.…

Machine Learning · Computer Science 2021-12-28 Nicholas P Baskerville , Diego Granziol , Jonathan P Keating

Recently, researchers observed that gradient descent for deep neural networks operates in an ``edge-of-stability'' (EoS) regime: the sharpness (maximum eigenvalue of the Hessian) is often larger than stability threshold $2/\eta$ (where…

Machine Learning · Computer Science 2023-02-22 Xingyu Zhu , Zixuan Wang , Xiang Wang , Mo Zhou , Rong Ge

Hybrid modeling, the combination of machine learning models and scientific mathematical models, enables flexible and robust data-driven prediction with partial interpretability. However, effectively the scientific models may be ignored in…

Machine Learning · Computer Science 2026-02-09 Naoya Takeishi

In this paper we model the loss function of high-dimensional optimization problems by a Gaussian random field, or equivalently a Gaussian process. Our aim is to study gradient descent in such loss functions or energy landscapes and compare…

Machine Learning · Statistics 2018-03-28 Mariano Chouza , Stephen Roberts , Stefan Zohren

Weight normalization (WeightNorm) is widely used in practice for the training of deep neural networks and modern deep learning libraries have built-in implementations of it. In this paper, we provide the first theoretical characterizations…

Machine Learning · Computer Science 2025-01-22 Pedro Cisneros-Velarde , Zhijie Chen , Sanmi Koyejo , Arindam Banerjee

We propose a generic framework to calibrate accuracy and confidence of a prediction in deep neural networks through stochastic inferences. We interpret stochastic regularization using a Bayesian model, and analyze the relation between…

Machine Learning · Computer Science 2019-04-25 Seonguk Seo , Paul Hongsuck Seo , Bohyung Han

Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking. These phenomena appear across architectures -- in…

Machine Learning · Computer Science 2026-01-01 Alan Oursland

While it has not yet been proven, empirical evidence suggests that model generalization is related to local properties of the optima which can be described via the Hessian. We connect model generalization with the local property of a…

Machine Learning · Computer Science 2018-09-21 Huan Wang , Nitish Shirish Keskar , Caiming Xiong , Richard Socher

Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded…

Machine Learning · Statistics 2016-10-05 Yarin Gal , Zoubin Ghahramani

The importance of domain knowledge in enhancing model performance and making reliable predictions in the real-world is critical. This has led to an increased focus on specific model properties for interpretability. We focus on incorporating…

Machine Learning · Computer Science 2019-12-04 Akhil Gupta , Naman Shukla , Lavanya Marla , Arinbjörn Kolbeinsson , Kartik Yellepeddi

Existing methods of pruning deep neural networks focus on removing unnecessary parameters of the trained network and fine tuning the model afterwards to find a good solution that recovers the initial performance of the trained model. Unlike…

Machine Learning · Computer Science 2021-11-17 Abdolghani Ebrahimi , Diego Klabjan

To understand the dynamics of optimization in deep neural networks, we develop a tool to study the evolution of the entire Hessian spectrum throughout the optimization process. Using this, we study a number of hypotheses concerning…

Machine Learning · Computer Science 2019-01-30 Behrooz Ghorbani , Shankar Krishnan , Ying Xiao

We investigate the topics of sensitivity and robustness in feedforward and convolutional neural networks. Combining energy landscape techniques developed in computational chemistry with tools drawn from formal methods, we produce empirical…

Machine Learning · Statistics 2018-12-06 Timothy E. Wang , Yiming Gu , Dhagash Mehta , Xiaojun Zhao , Edgar A. Bernal

The backpropagation networks are notably susceptible to catastrophic forgetting, where networks tend to forget previously learned skills upon learning new ones. To address such the 'sensitivity-stability' dilemma, most previous efforts have…

Machine Learning · Computer Science 2021-10-12 Danruo Deng , Guangyong Chen , Jianye Hao , Qiong Wang , Pheng-Ann Heng