English
Related papers

Related papers: Connecting Parameter Magnitudes and Hessian Eigens…

200 papers

This paper considers decentralized optimization with application to machine learning on graphs. The growing size of neural network (NN) models has motivated prior works on decentralized stochastic gradient algorithms to incorporate…

Optimization and Control · Mathematics 2021-10-12 Arjun Ashok Rao , Hoi-To Wai

Pruning neural networks reduces inference time and memory costs. On standard hardware, these benefits will be especially prominent if coarse-grained structures, like feature maps, are pruned. We devise two novel saliency-based methods for…

Machine Learning · Computer Science 2023-09-26 Manuel Nonnenmacher , Thomas Pfeil , Ingo Steinwart , David Reeb

Neural models learn representations of high-dimensional data on low-dimensional manifolds. Multiple factors, including stochasticities in the training process, model architectures, and additional inductive biases, may induce different…

Machine Learning · Computer Science 2025-12-02 Hanlin Yu , Berfin Inal , Georgios Arvanitidis , Soren Hauberg , Francesco Locatello , Marco Fumero

Existing Masked Image Modeling methods apply fixed mask patterns to guide the self-supervised training. As those mask patterns resort to different criteria to depict image contents, sticking to a fixed pattern leads to a limited vision cues…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Zhanzhou Feng , Shiliang Zhang

Recent empirical and theoretical work has shown that the dynamics of the large eigenvalues of the training loss Hessian have some remarkably robust features across models and datasets in the full batch regime. There is often an early period…

Machine Learning · Computer Science 2025-02-04 Atish Agarwala , Jeffrey Pennington

Large width limits have been a recent focus of deep learning research: modulo computational practicalities, do wider networks outperform narrower ones? Answering this question has been challenging, as conventional networks gain…

Machine Learning · Computer Science 2021-11-09 Geoff Pleiss , John P. Cunningham

The Discrepancy of a hypergraph is the minimum attainable value, over two-colorings of its vertices, of the maximum absolute imbalance of any hyperedge. The Hereditary Discrepancy of a hypergraph, defined as the maximum discrepancy of a…

Data Structures and Algorithms · Computer Science 2014-07-24 Aleksandar Nikolov , Kunal Talwar

Due to the effectiveness of second-order algorithms in solving classical optimization problems, designing second-order optimizers to train deep neural networks (DNNs) has attracted much research interest in recent years. However, because of…

Machine Learning · Computer Science 2024-03-06 Ying Sun , Hongwei Yong , Lei Zhang

Deep learning methods minimise the empirical risk using loss functions such as the cross entropy loss. When minimising the empirical risk, the generalisation of the learnt function still depends on the performance on the training data, the…

Machine Learning · Computer Science 2022-01-19 Antonio Jimeno Yepes

Learning parameters from voluminous data can be prohibitive in terms of memory and computational requirements. We propose a "compressive learning" framework where we estimate model parameters from a sketch of the training data. This sketch…

Machine Learning · Computer Science 2017-05-08 Nicolas Keriven , Anthony Bourrier , Rémi Gribonval , Patrick Pérez

We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the…

Over-parameterized neural networks generalize well in practice without any explicit regularization. Although it has not been proven yet, empirical evidence suggests that implicit regularization plays a crucial role in deep learning and…

Machine Learning · Computer Science 2019-03-07 Masayoshi Kubo , Ryotaro Banno , Hidetaka Manabe , Masataka Minoji

In this work we develop a Hessian-based sampling method for the construction of goal-oriented reduced order models with high-dimensional parameter inputs. Model reduction is known very challenging for high-dimensional parametric problems…

Numerical Analysis · Mathematics 2018-09-28 Peng Chen , Omar Ghattas

A good measure of similarity between data points is crucial to many tasks in machine learning. Similarity and metric learning methods learn such measures automatically from data, but they do not scale well respect to the dimensionality of…

Machine Learning · Computer Science 2019-09-10 Kuan Liu , Aurélien Bellet , Fei Sha

This paper studies identifiability and convergence behaviors for parameters of multiple types in finite mixtures, and the effects of model fitting with extra mixing components. First, we present a general theory for strong identifiability,…

Statistics Theory · Mathematics 2015-01-13 Nhat Ho , XuanLong Nguyen

We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. In contrast to weight or filter-level pruning, layer pruning reduces the harder to parallelize…

Machine Learning · Computer Science 2024-06-10 Valentin Frank Ingmar Guenter , Athanasios Sideris

Information distances like the Hellinger distance and the Jensen-Shannon divergence have deep roots in information theory and machine learning. They are used extensively in data analysis especially when the objects being compared are high…

Data Structures and Algorithms · Computer Science 2015-03-19 Amirali Abdullah , Ravi Kumar , Andrew McGregor , Sergei Vassilvitskii , Suresh Venkatasubramanian

We propose a deep hashing framework for sketch retrieval that, for the first time, works on a multi-million scale human sketch dataset. Leveraging on this large dataset, we explore a few sketch-specific traits that were otherwise…

Computer Vision and Pattern Recognition · Computer Science 2018-04-05 Peng Xu , Yongye Huang , Tongtong Yuan , Kaiyue Pang , Yi-Zhe Song , Tao Xiang , Timothy M. Hospedales , Zhanyu Ma , Jun Guo

Covariance and Hessian matrices have been analyzed separately in the literature for classification problems. However, integrating these matrices has the potential to enhance their combined power in improving classification performance. We…

Machine Learning · Computer Science 2024-10-10 Agus Hartoyo , Jan Argasiński , Aleksandra Trenk , Kinga Przybylska , Anna Błasiak , Alessandro Crimi

When training neural networks with full-batch gradient descent (GD) and step size $\eta$, the largest eigenvalue of the Hessian -- the sharpness $S(\boldsymbol{\theta})$ -- rises to $2/\eta$ and hovers there, a phenomenon termed the Edge of…

Machine Learning · Computer Science 2026-04-24 Fangshuo Liao , Afroditi Kolomvaki , Anastasios Kyrillidis