English
Related papers

Related papers: Learning on Transformers is Provable Low-Rank and …

200 papers

Signal models based on sparsity, low-rank and other properties have been exploited for image reconstruction from limited and corrupted data in medical imaging and other computational imaging applications. In particular, sparsifying…

Image and Video Processing · Electrical Eng. & Systems 2020-01-08 Xuehang Zheng , Saiprasad Ravishankar , Yong Long , Marc Louis Klasky , Brendt Wohlberg

Transformers have achieved state-of-the-art performance in language modeling tasks. However, the reasons behind their tremendous success are still unclear. In this paper, towards a better understanding, we train a Transformer model on a…

Machine Learning · Statistics 2024-06-06 Michael E. Sander , Raja Giryes , Taiji Suzuki , Mathieu Blondel , Gabriel Peyré

As deep neural networks are increasingly used in applications suited for low-power devices, a fundamental dilemma becomes apparent: the trend is to grow models to absorb increasing data that gives rise to memory intensive; however low-power…

Computer Vision and Pattern Recognition · Computer Science 2023-02-21 Weiyu Guo , Jiabin Ma , Liang Wang , Yongzhen Huang

We consider the task of low-multilinear-rank functional regression, i.e., learning a low-rank parametric representation of functions from scattered real-valued data. Our first contribution is the development and analysis of an efficient…

Computation · Statistics 2018-09-26 Alex A. Gorodetsky , John D. Jakeman

We study low-rank matrix regression in settings where matrix-valued predictors and scalar responses are observed across multiple individuals. Rather than assuming a fully homogeneous coefficient matrices across individuals, we accommodate…

Methodology · Statistics 2025-10-28 Di Wang , Xiaoyu Zhang , Guodong Li , Wenyang Zhang

Sparse auto-encoders are useful for extracting low-dimensional representations from high-dimensional data. However, their performance degrades sharply when the input noise at test time differs from the noise employed during training. This…

Machine Learning · Computer Science 2024-07-01 Nelson Goldenstein , Jeremias Sulam , Yaniv Romano

Deep neural networks often have millions of parameters. This can hinder their deployment to low-end devices, not only due to high memory requirements but also because of increased latency at inference. We propose a novel model compression…

Machine Learning · Computer Science 2020-06-15 Tao Lin , Sebastian U. Stich , Luis Barba , Daniil Dmitriev , Martin Jaggi

We study parameter estimation in Nonlinear Factor Analysis (NFA) where the generative model is parameterized by a deep neural network. Recent work has focused on learning such models using inference (or recognition) networks; we identify a…

Machine Learning · Statistics 2017-10-18 Rahul G. Krishnan , Dawen Liang , Matthew Hoffman

Existing generalization measures that aim to capture a model's simplicity based on parameter counts or norms fail to explain generalization in overparameterized deep neural networks. In this paper, we introduce a new, theoretically…

Machine Learning · Computer Science 2021-03-11 Lorenz Kuhn , Clare Lyle , Aidan N. Gomez , Jonas Rothfuss , Yarin Gal

Low-rank approximation of a matrix by means of random sampling has been consistently efficient in its empirical studies by many scientists who applied it with various sparse and structured multipliers, but adequate formal support for this…

Numerical Analysis · Mathematics 2016-06-07 Victor Y. Pan , Liang Zhao

Neural network pruning has shown to be an effective technique for reducing the network size, trading desirable properties like generalization and robustness to adversarial attacks for higher sparsity. Recent work has claimed that…

Machine Learning · Computer Science 2023-10-13 Giorgio Piras , Maura Pintor , Ambra Demontis , Battista Biggio

Transformers allow attention between all pairs of tokens, but there is reason to believe that most of these connections - and their quadratic time and memory - may not be necessary. But which ones? We evaluate the impact of sparsification…

Computation and Language · Computer Science 2022-10-11 Siddhartha Brahma , Polina Zablotskaia , David Mimno

Compressing transformer weights makes large language models cheaper to deploy. But each layer's compression introduces an error. These errors accumulate as the signal passes through later layers, and how they accumulate is not well…

Machine Learning · Computer Science 2026-05-08 Abhinaba Basu , Kumkum Basu , Koushik Deb

Transformers have demonstrated effectiveness in in-context solving data-fitting problems from various (latent) models, as reported by Garg et al. However, the absence of an inherent iterative structure in the transformer architecture…

Machine Learning · Computer Science 2024-03-19 Liu Yang , Kangwook Lee , Robert Nowak , Dimitris Papailiopoulos

Data is said to follow the transform (or analysis) sparsity model if it becomes sparse when acted on by a linear operator called a sparsifying transform. Several algorithms have been designed to learn such a transform directly from data,…

Machine Learning · Statistics 2019-01-30 Luke Pfister , Yoram Bresler

Linear encoding of sparse vectors is widely popular, but is commonly data-independent -- missing any possible extra (but a priori unknown) structure beyond sparsity. In this paper we present a new method to learn linear encoders that adapt…

Transformers often fail to learn generalizable algorithms, instead relying on brittle heuristics. Using graph connectivity as a testbed, we explain this phenomenon both theoretically and empirically. We consider a simplified Transformer…

Machine Learning · Computer Science 2026-02-19 Qilin Ye , Deqing Fu , Robin Jia , Vatsal Sharan

In this paper, we question the rationale behind propagating large numbers of parameters through a distributed system during federated learning. We start by examining the rank characteristics of the subspace spanned by gradients across…

Machine Learning · Computer Science 2022-02-02 Sheikh Shams Azam , Seyyedali Hosseinalipour , Qiang Qiu , Christopher Brinton

Transformer architecture has gained popularity due to its ability to scale with large dataset. Consequently, there is a need to reduce the model size and latency, especially for on-device deployment. We focus on vision transformer proposed…

Computer Vision and Pattern Recognition · Computer Science 2022-03-28 Ankur Kumar

Many types of neural network layers rely on matrix properties such as invertibility or orthogonality. Retaining such properties during optimization with gradient-based stochastic optimizers is a challenging task, which is usually addressed…

Machine Learning · Statistics 2020-12-02 Andreas Krämer , Jonas Köhler , Frank Noé
‹ Prev 1 4 5 6 7 8 10 Next ›