English
Related papers

Related papers: Improved Generalization Bound and Learning of Spar…

200 papers

Large Language Model (LLM) unlearning aims to remove targeted knowledge from a trained model, but practical deployments often require post-training quantization (PTQ) for efficient inference. However, aggressive low-bit PTQ can mask…

Low-Rank Adaptation (LoRA) enables efficient fine-tuning of pre-trained language models through low-rank matrix approximation, achieving effectiveness in many scenarios. However, its representation capacity is constrained in complex tasks…

Parameter-efficient fine-tuning (PEFT) methods, such as LoRA, offer compact and effective alternatives to full model fine-tuning by introducing low-rank updates to pre-trained weights. However, most existing approaches rely on global low…

Machine Learning · Computer Science 2025-09-25 Babak Barazandeh , Subhabrata Majumdar , Om Rajyaguru , George Michailidis

We study lower bounds on adaptive sensing algorithms for recovering low rank matrices using linear measurements. Given an $n \times n$ matrix $A$, a general linear measurement $S(A)$, for an $n \times n$ matrix $S$, is just the inner…

Data Structures and Algorithms · Computer Science 2024-02-21 Praneeth Kacham , David P Woodruff

Regularized regression approaches such as the Lasso have been widely adopted for constructing sparse linear models in high-dimensional datasets. A complexity in fitting these models is the tuning of the parameters which control the level of…

Methodology · Statistics 2019-03-12 Ellis Patrick , Samuel Mueller

This paper concerns quasi-stochastic approximation (QSA) to solve root finding problems commonly found in applications to optimization and reinforcement learning. The general constant gain algorithm may be expressed as the…

Optimization and Control · Mathematics 2024-04-02 Caio Kalil Lauand , Sean Meyn

A low-rank transformation learning framework for subspace clustering and classification is here proposed. Many high-dimensional data, such as face images and motion sequences, approximately lie in a union of low-dimensional subspaces. The…

Computer Vision and Pattern Recognition · Computer Science 2014-03-11 Qiang Qiu , Guillermo Sapiro

The rapid advancement of foundation modelslarge-scale neural networks trained on diverse, extensive datasetshas revolutionized artificial intelligence, enabling unprecedented advancements across domains such as natural language processing,…

High-dimensional statistical learning (HDSL) has wide applications in data analysis, operations research, and decision-making. Despite the availability of multiple theoretical frameworks, most existing HDSL schemes stipulate the following…

Statistics Theory · Mathematics 2021-10-25 Hongcheng Liu , Yinyu Ye , Hung Yi Lee

We propose a unified framework to solve general low-rank plus sparse matrix recovery problems based on matrix factorization, which covers a broad family of objective functions satisfying the restricted strong convexity and smoothness…

Machine Learning · Statistics 2018-02-21 Xiao Zhang , Lingxiao Wang , Quanquan Gu

High-dimensional linear bandits with low-dimensional structure have received considerable attention in recent studies due to their practical significance. The most common structure in the literature is sparsity. However, it may not be…

Machine Learning · Statistics 2026-01-01 Nam Phuong Tran , The Anh Ta , Debmalya Mandal , Long Tran-Thanh

Matrix sensing has many real-world applications in science and engineering, such as system control, distance embedding, and computer vision. The goal of matrix sensing is to recover a matrix $A_\star \in \mathbb{R}^{n \times n}$, based on a…

Data Structures and Algorithms · Computer Science 2023-03-23 Lianke Qin , Zhao Song , Ruizhe Zhang

In prior work, Gupta et al. (SPAA 2022) presented a distributed algorithm for multiplying sparse $n \times n$ matrices, using $n$ computers. They assumed that the input matrices are uniformly sparse--there are at most $d$ non-zeros in each…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-24 Chetan Gupta , Janne H. Korhonen , Jan Studený , Jukka Suomela , Hossein Vahidi

We investigate the generalization and optimization properties of shallow neural-network classifiers trained by gradient descent in the interpolating regime. Specifically, in a realizable scenario where model weights can achieve arbitrarily…

Machine Learning · Statistics 2023-03-29 Hossein Taheri , Christos Thrampoulidis

The learning rate in stochastic gradient methods is a critical hyperparameter that is notoriously costly to tune via standard grid search, especially for training modern large-scale models with billions of parameters. We identify a…

Machine Learning · Computer Science 2026-02-17 Amit Attia , Tomer Koren

We investigate LoRA in federated learning through the lens of the asymmetry analysis of the learned $A$ and $B$ matrices. In doing so, we uncover that $A$ matrices are responsible for learning general knowledge, while $B$ matrices focus on…

Machine Learning · Computer Science 2025-03-24 Pengxin Guo , Shuang Zeng , Yanran Wang , Huijie Fan , Feifei Wang , Liangqiong Qu

Low-rank adaptation (LoRA) has been prominently employed for parameter-efficient fine-tuning of large language models (LLMs). However, the limited expressive capacity of LoRA, stemming from the low-rank constraint, has been recognized as a…

Computation and Language · Computer Science 2025-03-18 Zhiwei He , Zhaopeng Tu , Xing Wang , Xingyu Chen , Zhijie Wang , Jiahao Xu , Tian Liang , Wenxiang Jiao , Zhuosheng Zhang , Rui Wang

In a low-rank linear bandit problem, the reward of an action (represented by a matrix of size $d_1 \times d_2$) is the inner product between the action and an unknown low-rank matrix $\Theta^*$. We propose an algorithm based on a novel…

Machine Learning · Statistics 2020-10-20 Yangyi Lu , Amirhossein Meisami , Ambuj Tewari

Parameter-efficient fine-tuning (PEFT) based on low-rank decomposition, such as LoRA, has become a standard for adapting large pretrained models. However, its behavior in sequential learning -- specifically regarding catastrophic forgetting…

Machine Learning · Computer Science 2026-03-11 Muhammad Ahmad , Jingjing Zheng , Yankai Cao

The prohibitive sizes of Large Language Models (LLMs) today make it difficult to deploy them on memory-constrained edge devices. This work introduces $\rm CALDERA$ -- a new post-training LLM compression algorithm that harnesses the inherent…

Machine Learning · Computer Science 2024-11-05 Rajarshi Saha , Naomi Sagan , Varun Srivastava , Andrea J. Goldsmith , Mert Pilanci