English
Related papers

Related papers: McTorch, a manifold optimization library for deep …

200 papers

The rapid growth in the size of deep learning models strains the capabilities of traditional dense computation paradigms. Leveraging sparse computation has become increasingly popular for training and deploying large-scale models, but…

Machine Learning · Computer Science 2024-06-21 Bobby Yan , Alexander J. Root , Trevor Gale , David Broman , Fredrik Kjolstad

Imposing explicit constraints is relatively new but increasingly pressing in deep learning, stimulated by, e.g., trustworthy AI that performs robust optimization over complicated perturbation sets and scientific applications that need to…

Machine Learning · Computer Science 2022-11-15 Buyun Liang , Tim Mitchell , Ju Sun

The constant introduction of standardized benchmarks in the literature has helped accelerating the recent advances in meta-learning research. They offer a way to get a fair comparison between different algorithms, and the wide range of…

Machine Learning · Computer Science 2019-09-17 Tristan Deleu , Tobias Würfl , Mandana Samiei , Joseph Paul Cohen , Yoshua Bengio

Optimization on manifolds is a class of methods for optimization of an objective function, subject to constraints which are smooth, in the sense that the set of points which satisfy the constraints admits the structure of a differentiable…

Mathematical Software · Computer Science 2020-09-03 James Townsend , Niklas Koep , Sebastian Weichwald

Multiple Instance Learning (MIL) is a powerful framework for weakly supervised learning, particularly useful when fine-grained annotations are unavailable. Despite growing interest in deep MIL methods, the field lacks standardized tools for…

While early AutoML frameworks focused on optimizing traditional ML pipelines and their hyperparameters, a recent trend in AutoML is to focus on neural architecture search. In this paper, we introduce Auto-PyTorch, which brings the best of…

Machine Learning · Computer Science 2021-04-27 Lucas Zimmer , Marius Lindauer , Frank Hutter

Orthogonal and 1-Lipschitz neural network layers are essential building blocks in robust deep learning architectures, crucial for certified adversarial robustness, stable generative models, and reliable recurrent networks. Despite…

Machine Learning · Computer Science 2026-01-21 Thibaut Boissin , Franck Mamalet , Valentin Lafargue , Mathieu Serrurier

Tensor networks are factorizations of high-dimensional tensors into networks of smaller tensors. They have applications in physics and mathematics, and recently have been proposed as promising machine learning architectures. To ease the…

Machine Learning · Computer Science 2024-06-12 José Ramón Pareja Monturiol , David Pérez-García , Alejandro Pozas-Kerstjens

The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning…

Computation and Language · Computer Science 2020-02-04 Alexander M. Rush

Continual learning is the problem of learning from a nonstationary stream of data, a fundamental issue for sustainable and efficient training of deep neural networks over time. Unfortunately, deep learning libraries only provide primitives…

Machine Learning · Computer Science 2023-02-06 Antonio Carta , Lorenzo Pellegrini , Andrea Cossu , Hamed Hemati , Vincenzo Lomonaco

We present MLRG Deep Curvature suite, a PyTorch-based, open-source package for analysis and visualisation of neural network curvature and loss landscape. Despite of providing rich information into properties of neural network and useful for…

Machine Learning · Statistics 2020-05-26 Diego Granziol , Xingchen Wan , Timur Garipov

This paper presents the design, implementation, and evaluation of the PyTorch distributed data parallel module. PyTorch is a widely-adopted scientific computing package used in deep learning research and applications. Recent advances in…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-06-30 Shen Li , Yanli Zhao , Rohan Varma , Omkar Salpekar , Pieter Noordhuis , Teng Li , Adam Paszke , Jeff Smith , Brian Vaughan , Pritam Damania , Soumith Chintala

We present tntorch, a tensor learning framework that supports multiple decompositions (including Candecomp/Parafac, Tucker, and Tensor Train) under a unified interface. With our library, the user can learn and handle low-rank tensors with…

Machine Learning · Computer Science 2022-09-22 Mikhail Usvyatsov , Rafael Ballester-Ripoll , Konrad Schindler

Solving complex computer vision tasks by deep learning techniques relies on large amounts of (supervised) image data, typically unavailable in industrial environments. The lack of training data starts to impede the successful transfer of…

Computer Vision and Pattern Recognition · Computer Science 2020-10-23 Christoph Heindl , Lukas Brunner , Sebastian Zambal , Josef Scharinger

Automatic differentiation frameworks are optimized for exactly one thing: computing the average mini-batch gradient. Yet, other quantities such as the variance of the mini-batch gradients or many approximations to the Hessian can, in…

Machine Learning · Computer Science 2020-02-18 Felix Dangel , Frederik Kunstner , Philipp Hennig

We introduce torchbearer, a model fitting library for pytorch aimed at researchers working on deep learning or differentiable programming. The torchbearer library provides a high level metric and callback API that can be used for a wide…

Machine Learning · Computer Science 2018-09-11 Ethan Harris , Matthew Painter , Jonathon Hare

Designing deep learning-based solutions is becoming a race for training deeper models with a greater number of layers. While a large-size deeper model could provide competitive accuracy, it creates a lot of logistical challenges and…

There has been a considerable interest in constrained training of deep neural networks (DNNs) recently for applications such as fairness and safety. Several toolkits have been proposed for this task, yet there is still no industry standard.…

Machine Learning · Computer Science 2025-09-26 Andrii Kliachkin , Jana Lepšová , Gilles Bareilles , Jakub Mareček

We address the problem of performing backpropagation for computation graphs involving 3D transformation groups SO(3), SE(3), and Sim(3). 3D transformation groups are widely used in 3D vision and robotics, but they do not form vector spaces…

Computer Vision and Pattern Recognition · Computer Science 2021-03-26 Zachary Teed , Jia Deng

This work presents TorchRadon -- an open source CUDA library which contains a set of differentiable routines for solving computed tomography (CT) reconstruction problems. The library is designed to help researchers working on CT problems to…

Image and Video Processing · Electrical Eng. & Systems 2020-10-01 Matteo Ronchetti