English
Related papers

Related papers: Spectral Tensor Train Parameterization of Deep Lea…

200 papers

Can we use sparse tokens for dense prediction, e.g., segmentation? Although token sparsification has been applied to Vision Transformers (ViT) to accelerate classification, it is still unknown how to perform segmentation from sparse tokens.…

Computer Vision and Pattern Recognition · Computer Science 2023-03-14 Lei Zhou , Huidong Liu , Joseph Bae , Junjun He , Dimitris Samaras , Prateek Prasanna

The components underpinning PLMs -- large weight matrices -- were shown to bear considerable redundancy. Matrix factorization, a well-established technique from matrix theory, has been utilized to reduce the number of parameters in PLM.…

Computation and Language · Computer Science 2023-06-27 Siyu Ren , Kenny Q. Zhu

Tensor completion estimates missing components by exploiting the low-rank structure of multi-way data. The recently proposed methods based on tensor train (TT) and tensor ring (TR) show better performance in image recovery than classical…

Machine Learning · Computer Science 2020-04-24 Huyan Huang , Yipeng Liu , Ce Zhu

Despite the remarkable success of deep learning in pattern recognition, deep network models face the problem of training a large number of parameters. In this paper, we propose and evaluate a novel multi-path wavelet neural network…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 D. D. N. De Silva , H. W. M. K. Vithanage , K. S. D. Fernando , I. T. S. Piyatilake

The reduced-rank method exploits the distortion-variance tradeoff to yield superior solutions for classic problems in statistical signal processing such as parameter estimation and filtering. The central idea is to reduce the variance of…

Information Theory · Computer Science 2019-03-06 K. G. Nagananda , Pramod Khargonekar

Foundation models have achieved remarkable success, yet their growing parameter counts pose significant computational and memory challenges. Low-rank factorization offers a promising route to reduce training and inference costs, but the…

Machine Learning · Computer Science 2026-02-16 Paul Janson , Edouard Oyallon , Eugene Belilovsky

Continuous neural representations have recently emerged as a powerful and flexible alternative to classical discretized representations of signals. However, training them to capture fine details in multi-scale signals is difficult and…

Machine Learning · Computer Science 2022-10-06 Sifan Wang , Hanwen Wang , Jacob H. Seidman , Paris Perdikaris

Approximating a tensor in the tensor train (TT) format has many important applications in scientific computing. Rounding a TT tensor involves further compressing a tensor that is already in the TT format. This paper proposes new randomized…

Weight tying, i.e. sharing parameters between input and output embedding matrices, is common practice in language model design, yet its impact on the learned embedding space remains poorly understood. In this paper, we show that tied…

Computation and Language · Computer Science 2026-03-30 Antonio Lopardo , Avyukth Harish , Catherine Arnett , Akshat Gupta

Deep learning has been wildly successful in practice and most state-of-the-art machine learning methods are based on neural networks. Lacking, however, is a rigorous mathematical theory that adequately explains the amazing performance of…

Machine Learning · Statistics 2023-10-03 Rahul Parhi , Robert D. Nowak

We explore the applications of random matrix theory (RMT) in the training of deep neural networks (DNNs), focusing on layer pruning that is reducing the number of DNN parameters (weights). Our numerical results show that this pruning leads…

Machine Learning · Computer Science 2024-09-10 Leonid Berlyand , Etienne Sandier , Yitzchak Shmalo , Lei Zhang

We describe a simple and general neural network weight compression approach, in which the network parameters (weights and biases) are represented in a "latent" space, amounting to a reparameterization. This space is equipped with a learned…

Machine Learning · Computer Science 2020-02-18 Deniz Oktay , Johannes Ballé , Saurabh Singh , Abhinav Shrivastava

Approaches for compressing large-language models using low-rank decomposition have made strides, particularly with the introduction of activation and loss-aware SVD, which improves the trade-off between decomposition rank and downstream…

Machine Learning · Computer Science 2025-12-17 Sidhant Sundrani , Francesco Tudisco , Pasquale Minervini

Based on the continuous interpretation of deep learning cast as an optimal control problem, this paper investigates the benefits of employing B-spline basis functions to parameterize neural network controls across the layers. Rather than…

Machine Learning · Computer Science 2021-03-02 Stefanie Günther , Will Pazner , Dongping Qi

In machine learning practice it is often useful to identify relevant input features. Isolating key input elements, ranked according their respective degree of relevance, can help to elaborate on the process of decision making. Here, we…

Machine Learning · Computer Science 2025-11-24 Lorenzo Chicchi , Lorenzo Buffoni , Diego Febbe , Lorenzo Giambagli , Raffaele Marino , Duccio Fanelli

Unlike 2D raster images, there is no single dominant representation for 3D visual data processing. Different formats like point clouds, meshes, or implicit functions each have their strengths and weaknesses. Still, grid representations such…

Computer Vision and Pattern Recognition · Computer Science 2022-10-06 Mikhail Usvyatsov , Rafael Ballester-Rippoll , Lina Bashaeva , Konrad Schindler , Gonzalo Ferrer , Ivan Oseledets

We propose a method for efficiently incorporating constraints into a stochastic gradient Langevin framework for the training of deep neural networks. Constraints allow direct control of the parameter space of the model. Appropriately…

Machine Learning · Computer Science 2021-06-22 Benedict Leimkuhler , Timothée Pouchon , Tiffany Vlaar , Amos Storkey

We develop both first and second order numerical optimization methods to solve non-smooth optimization problems featuring a shared sparsity penalty, constrained by differential equations with uncertainty. To alleviate the curse of…

Optimization and Control · Mathematics 2025-09-18 Harbir Antil , Sergey Dolgov , Akwum Onwunta

Despite their high accuracy, complex neural networks demand significant computational resources, posing challenges for deployment on resource constrained devices such as mobile phones and embedded systems. Compression algorithms have been…

Machine Learning · Computer Science 2025-09-23 Ali Aghababaei-Harandi , Massih-Reza Amini

Tensor networks are used to efficiently approximate states of strongly-correlated quantum many-body systems. More generally, tensor network approximations may allow to reduce the costs for operating on an order-$N$ tensor from exponential…

Strongly Correlated Electrons · Physics 2022-05-31 Hao Chen , Thomas Barthel
‹ Prev 1 8 9 10 Next ›