English
Related papers

Related papers: An Augmented Backward-Corrected Projector Splittin…

200 papers

Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of…

Computer Vision and Pattern Recognition · Computer Science 2020-03-26 Abhinav Goel , Caleb Tung , Yung-Hsiang Lu , George K. Thiruvathukal

Building upon the success of low-rank adapter (LoRA), low-rank gradient projection (LoRP) has emerged as a promising solution for memory-efficient fine-tuning. However, existing LoRP methods typically treat each row of the gradient matrix…

Machine Learning · Computer Science 2025-05-06 Yezhen Wang , Zhouhao Yang , Brian K Chen , Fanyi Pu , Bo Li , Tianyu Gao , Kenji Kawaguchi

Magnetic Resonance (MR) Fingerprinting is an emerging multi-parametric quantitative MR imaging technique, for which image reconstruction methods utilizing low-rank and subspace constraints have achieved state-of-the-art performance.…

Image and Video Processing · Electrical Eng. & Systems 2023-05-26 Hengfa Lu , Huihui Ye , Lawrence L. Wald , Bo Zhao

This paper proposes a differentiable robust LQR layer for reinforcement learning and imitation learning under model uncertainty and stochastic dynamics. The robust LQR layer can exploit the advantages of robust optimal control and…

Robotics · Computer Science 2021-06-11 Ngo Anh Vien , Gerhard Neumann

Despite advances using low-rank adapters and quantization, pretraining of large models on consumer hardware has not been possible without model sharding, offloading during training, or per-layer gradient updates. To address these…

Machine Learning · Computer Science 2024-11-05 Sebastian Loeschcke , Mads Toftrup , Michael J. Kastoryano , Serge Belongie , Vésteinn Snæbjarnarson

Post-training quantization (PTQ) has emerged as a prevailing technique for deploying large language models (LLMs) efficiently in terms of both memory and computation, across edge devices and server platforms. Existing PTQ methods primarily…

Machine Learning · Computer Science 2026-03-10 Yeonsik Park , Hyeonseong Kim , Seungkyu Choi

This paper introduces a novel computational approach termed the Reduced Augmentation Implicit Low-rank (RAIL) method by investigating two predominant research directions in low-rank solutions to time-dependent partial differential equations…

Numerical Analysis · Mathematics 2024-09-12 Joseph Nakao , Jing-Mei Qiu , Lukas Einkemmer

Low-rank matrix decomposition has gained great popularity recently in scaling up kernel methods to large amounts of data. However, some limitations could prevent them from working effectively in certain domains. For example, many existing…

Machine Learning · Computer Science 2012-08-27 Kai Zhang , Liang Lan , Jun Liu , andreas Rauber , Fabian Moerchen

Compressing neural networks is a key step when deploying models for real-time or embedded applications. Factorizing the model's matrices using low-rank approximations is a promising method for achieving compression. While it is possible to…

Machine Learning · Computer Science 2023-10-20 Lucas Maison , Hélion du Mas des Bourboux , Thomas Courtat

Deployment of neural networks on resource-constrained devices demands models that are both compact and robust to adversarial inputs. However, compression and adversarial robustness often conflict. In this work, we introduce a dynamical…

Machine Learning · Computer Science 2025-09-24 Steffen Schotthöfer , H. Lexie Yang , Stefan Schnake

We consider the problem of approximating an affinely structured matrix, for example a Hankel matrix, by a low-rank matrix with the same structure. This problem occurs in system identification, signal processing and computer algebra, among…

Numerical Analysis · Mathematics 2014-06-25 Mariya Ishteva , Konstantin Usevich , Ivan Markovsky

The efficient compression of large language models (LLMs) has become increasingly popular. However, recovering the performance of compressed LLMs remains a major challenge. The current practice in LLM compression entails the implementation…

Computation and Language · Computer Science 2024-12-17 Changhai Zhou , Shijie Han , Lining Yang , Yuhua Zhou , Xu Cheng , Yibin Wang , Hongguang Li

The low-rank matrix factorization as a L1 norm minimization problem has recently attracted much attention due to its intrinsic robustness to the presence of outliers and missing data. In this paper, we propose a new method, called the…

Numerical Analysis · Computer Science 2012-04-26 Deyu Meng , Zongben Xu

Nonnegative matrix factorization (NMF) is a powerful technique for dimension reduction, extracting latent factors and learning part-based representation. For large datasets, NMF performance depends on some major issues: fast algorithms,…

Optimization and Control · Mathematics 2015-07-01 Duy-Khuong Nguyen , Tu-Bao Ho

Low-Rank Adaptation (LoRA) lowers the computational and memory overhead of fine-tuning large models by updating a low-dimensional subspace of the pre-trained weight matrix. Albeit efficient, LoRA exhibits suboptimal convergence and…

Machine Learning · Computer Science 2026-02-25 Yilang Zhang , Bingcong Li , Georgios B. Giannakis

We propose a dynamical low-rank algorithm for a gyrokinetic model that is used to describe strongly magnetized plasmas. The low-rank approximation is based on a decomposition into variables parallel and perpendicular to the magnetic field,…

Computational Physics · Physics 2023-07-03 Lukas Einkemmer

Distributed training of foundation models via $\texttt{DDP}$ is limited by interconnect bandwidth. While infrequent communication strategies reduce synchronization frequency, they remain bottlenecked by the memory and communication…

Reinforcement learning with verifiable rewards (RLVR) has become a trending paradigm for training reasoning large language models (LLMs). However, due to the autoregressive decoding nature of LLMs, the rollout process becomes the efficiency…

Machine Learning · Computer Science 2026-02-17 Yuhang Li , Reena Elangovan , Xin Dong , Priyadarshini Panda , Brucek Khailany

In the pursuit of reducing the number of trainable parameters in deep transformer networks, we employ Reinforcement Learning to dynamically select layers during training and tie them together. Every few iterations, the RL agent is asked…

Machine Learning · Computer Science 2024-01-24 Tamir David Hay , Lior Wolf

Operating deep neural networks (DNNs) on devices with limited resources requires the reduction of their memory as well as computational footprint. Popular reduction methods are network quantization or pruning, which either reduce the word…

‹ Prev 1 4 5 6 7 8 10 Next ›