English
Related papers

Related papers: Information Geometry of Orthogonal Initializations…

200 papers

In low-latency or mobile applications, lower computation complexity, lower memory footprint and better energy efficiency are desired. Many prior works address this need by removing redundant parameters. Parameter quantization replaces…

Machine Learning · Computer Science 2021-11-16 Cheng-Chou Lan

A candidate explanation of the good empirical performance of deep neural networks is the implicit regularization effect of first order optimization methods. Inspired by this, we prove a convergence theorem for nonconvex composite…

Machine Learning · Computer Science 2023-02-14 Dávid Terjék , Diego González-Sánchez

In this work we propose an extension of physics informed supervised learning strategies to parametric partial differential equations. Indeed, even if the latter are indisputably useful in many applications, they can be computationally…

Machine Learning · Computer Science 2024-01-22 Nicola Demo , Maria Strazzullo , Gianluigi Rozza

The successful training of neural networks hinges on the use of first order optimization methods, yet the theoretical characterization of these methods remains incomplete. This is especially true in settings with mild overparameterization.…

Machine Learning · Computer Science 2026-05-27 James Town , Etienne Boursier , Ben Lewis , Matthias Englert , Ranko Lazic

Training neural networks requires significant computational resources and energy. Methods like mixed-precision and quantization-aware training reduce bit usage, yet they still depend heavily on computationally expensive gradient-based…

Machine Learning · Computer Science 2025-09-30 Noa Cohen , Omkar Joglekar , Dotan Di Castro , Vladimir Tchuiev , Shir Kozlovsky , Michal Moshkovitz

We propose a custom learning algorithm for shallow over-parameterized neural networks, i.e., networks with single hidden layer having infinite width. The infinite width of the hidden layer serves as an abstraction for the…

Machine Learning · Computer Science 2023-12-19 Alexis Teter , Iman Nodozi , Abhishek Halder

Recent work has highlighted the role of initialization scale in determining the structure of the solutions that gradient methods converge to. In particular, it was shown that large initialization leads to the neural tangent kernel regime…

Machine Learning · Computer Science 2021-02-22 Shahar Azulay , Edward Moroshko , Mor Shpigel Nacson , Blake Woodworth , Nathan Srebro , Amir Globerson , Daniel Soudry

This paper investigates how the compositional structure of neural networks shapes their optimization landscape and training dynamics. We analyze the gradient flow associated with overparameterized optimization problems, which can be…

Machine Learning · Computer Science 2025-11-14 Arthur Castello Branco de Oliveira , Dhruv Jatkar , Eduardo Sontag

In deep learning, neural networks serve as noisy channels between input data and its representation. This perspective naturally relates deep learning with the pursuit of constructing channels with optimal performance in information…

Machine Learning · Computer Science 2022-12-06 Kangyu Weng , Aohua Cheng , Ziyang Zhang , Pei Sun , Yang Tian

While large machine learning models have shown remarkable performance in various domains, their training typically requires iterating for many passes over the training data. However, due to computational and memory constraints and potential…

Machine Learning · Computer Science 2025-11-04 Youngjae Min , Namhoon Cho , Navid Azizan

This study explores the learning dynamics of neural networks by analyzing the singular value decomposition (SVD) of their weights throughout training. Our investigation reveals that an orthogonal basis within each multidimensional weight's…

Machine Learning · Computer Science 2024-11-12 Daniel Coquelin , Katharina Flügel , Marie Weiel , Nicholas Kiefer , Charlotte Debus , Achim Streit , Markus Götz

A common method in training neural networks is to initialize all the weights to be independent Gaussian vectors. We observe that by instead initializing the weights into independent pairs, where each pair consists of two identical Gaussian…

Machine Learning · Computer Science 2022-06-28 Alexander Munteanu , Simon Omlor , Zhao Song , David P. Woodruff

Neural networks are discrete entities: subdivided into discrete layers and parametrized by weights which are iteratively optimized via difference equations. Recent work proposes networks with layer outputs which are no longer quantized but…

Neural and Evolutionary Computing · Computer Science 2019-09-09 Stefano Massaroli , Michael Poli , Federico Califano , Angela Faragasso , Jinkyoo Park , Atsushi Yamashita , Hajime Asama

Second-order optimization methods for training neural networks, such as KFAC, exhibit superior convergence by utilizing curvature information of loss landscape. However, it comes at the expense of high computational burden. In this work, we…

Machine Learning · Computer Science 2025-11-12 Hyunseok Seung , Jaewoo Lee , Hyunsuk Ko

We consider applications of neural networks in nonlinear system identification and formulate a hypothesis that adjusting general network structure by incorporating frequency information or other known orthogonal transform, should result in…

Machine Learning · Computer Science 2025-01-24 Krzysztof Zając , Wojciech Sopot , Paweł Wachel

The widespread use of neural networks across different scientific domains often involves constraining them to satisfy certain symmetries, conservation laws, or other domain knowledge. Such constraints are often imposed as soft penalties…

Machine Learning · Computer Science 2020-01-15 Sifan Wang , Yujun Teng , Paris Perdikaris

In deep learning, it is common to use more network parameters than training points. In such scenarioof over-parameterization, there are usually multiple networks that achieve zero training error so that thetraining algorithm induces an…

Machine Learning · Computer Science 2023-08-22 Hung-Hsu Chou , Carsten Gieshoff , Johannes Maly , Holger Rauhut

Machine learning is evolving towards high-order models that necessitate pre-training on extensive datasets, a process associated with significant overheads. Traditional models, despite having pre-trained weights, are becoming obsolete due…

Machine Learning · Computer Science 2024-05-10 Chenhui Xu , Xinyao Wang , Fuxun Yu , Jinjun Xiong , Xiang Chen

This paper seeks to answer the question: as the (near-) orthogonality of weights is found to be a favorable property for training deep convolutional neural networks, how can we enforce it in more effective and easy-to-use ways? We develop…

Machine Learning · Computer Science 2018-10-23 Nitin Bansal , Xiaohan Chen , Zhangyang Wang

Likelihood-based deep generative models such as score-based diffusion models and variational autoencoders are state-of-the-art machine learning models approximating high-dimensional distributions of data such as images, text, or audio. One…

Machine Learning · Statistics 2024-05-28 Sam Dauncey , Chris Holmes , Christopher Williams , Fabian Falck