English
Related papers

Related papers: Model-free Low-Rank Reinforcement Learning via Lev…

200 papers

Low-rank adaptations (LoRAs) have revolutionized the finetuning of large foundation models, enabling efficient adaptation even with limited computational resources. The resulting proliferation of LoRAs presents exciting opportunities for…

Machine Learning · Computer Science 2024-10-16 Theo Putterman , Derek Lim , Yoav Gelberg , Stefanie Jegelka , Haggai Maron

Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method validated across NLP and CV domains. However, LoRA faces an inherent low-rank bottleneck: narrowing its performance gap with full finetuning…

Machine Learning · Computer Science 2025-12-03 Haonan Dong , Wenhao Zhu , Guojie Song , Liang Wang

The use of low-rank adaptation (LoRA) with frozen pretrained language models (PLMs) has become increasing popular as a mainstream, resource-efficient modeling approach for memory-constrained hardware. In this study, we first explore how to…

Fine-tuning large pre-trained vision foundation models in a parameter-efficient manner is critical for downstream vision tasks, considering the practical constraints of computational and storage costs. Low-rank adaptation (LoRA) is a…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Houqiang Zhong , Shaocheng Shen , Ke Cai , Zhenglong Wu , Jiangchao Yao , Yuan Cheng , Xuefei Li , Xiaoyun Zhang , Li Song , Qiang Hu

We revisit continual learning~(CL), which enables pre-trained vision transformers (ViTs) to sequentially fine-tune on new downstream tasks over time. However, as the scale of these models increases, catastrophic forgetting remains a more…

Computer Vision and Pattern Recognition · Computer Science 2026-03-25 Huancheng Chen , Jingtao Li , Weiming Zhuang , Chen Chen , Lingjuan Lyu

Classifying Non-Functional Requirements (NFRs) in software development life cycle is critical. Inspired by the theory of transfer learning, researchers apply powerful pre-trained models for NFR classification. However, full fine-tuning by…

Software Engineering · Computer Science 2025-03-12 Xia Li , Allen Kim

This article is an extended version of previous work of the authors [40, 41] on low-rank matrix estimation in the presence of constraints on the factors into which the matrix is factorized. Low-rank matrix factorization is one of the basic…

Statistics Theory · Mathematics 2017-08-28 Thibault Lesieur , Florent Krzakala , Lenka Zdeborová

This work presents In-Context Policy Iteration, an algorithm for performing Reinforcement Learning (RL), in-context, using foundation models. While the application of foundation models to RL has received considerable attention, most…

Machine Learning · Computer Science 2023-08-15 Ethan Brooks , Logan Walls , Richard L. Lewis , Satinder Singh

Low-rank adaptation (LoRA) is widely used for parameter-efficient fine-tuning, but its standard all-token, all-head design ignores the heterogeneous structure of vision language model (VLM) inputs. We introduce \emph{Image-LoRA}, a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Tiange Luo , Lajanugen Logeswaran , Jaekyeom Kim , Justin Johnson , Honglak Lee

We develop two iterative algorithms for solving the low rank phase retrieval (LRPR) problem. LRPR refers to recovering a low-rank matrix $\X$ from magnitude-only (phaseless) measurements of random linear projections of its columns. Both…

Information Theory · Computer Science 2017-08-02 Namrata Vaswani , Seyedehsara Nayer , Yonina C. Eldar

We study algorithms for estimating the statistical leverage scores of rectangular dense or sparse matrices of arbitrary rank. Our approach is based on combining rank revealing methods with compositions of dense and sparse randomized…

Data Structures and Algorithms · Computer Science 2022-03-08 Aleksandros Sobczyk , Efstratios Gallopoulos

Low-rank adaptation (LoRA) is a popular method for fine-tuning large-scale pre-trained models in downstream tasks by learning low-rank incremental matrices. Though LoRA and its variants effectively reduce the number of trainable parameters…

Machine Learning · Computer Science 2024-03-21 Rushi Qiang , Ruiyi Zhang , Pengtao Xie

Parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) have become essential for deploying large language models, yet their static parameter allocation remains suboptimal for inputs of varying complexity. We present…

Machine Learning · Computer Science 2026-05-05 Zongqian Li , Yixuan Su , Han Zhou , Zihao Fu , Nigel Collier

During initial iterations of training in most Reinforcement Learning (RL) algorithms, agents perform a significant number of random exploratory steps. In the real world, this can limit the practicality of these algorithms as it can lead to…

Machine Learning · Computer Science 2022-10-17 Ashish Kumar Jayant , Shalabh Bhatnagar

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…

Machine Learning · Computer Science 2025-07-15 Seokmin Ko

We develop several provably efficient model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov Decision Processes (MDPs). We consider both online setting and the setting with access to a simulator. In the…

Machine Learning · Computer Science 2023-06-29 Zihan Zhang , Qiaomin Xie

Fine-tuning helps large language models (LLM) recover degraded information and enhance task performance. Although Low-Rank Adaptation (LoRA) is widely used and effective for fine-tuning, we have observed that its scaling factor can limit or…

Machine Learning · Computer Science 2025-01-14 Jun Liu , Zhenglun Kong , Peiyan Dong , Changdi Yang , Xuan Shen , Pu Zhao , Hao Tang , Geng Yuan , Wei Niu , Wenbin Zhang , Xue Lin , Dong Huang , Yanzhi Wang

Low-rank structure is a common implicit assumption in many modern reinforcement learning (RL) algorithms. For instance, reward-free and goal-conditioned RL methods often presume that the successor measure admits a low-rank representation.…

Machine Learning · Computer Science 2025-11-06 Bastien Dubail , Stefan Stojanovic , Alexandre Proutière

In this paper, we show that Low Rank Adaptation (LoRA) as originally introduced in Hu et al. (2021) leads to suboptimal finetuning of models with large width (embedding dimension). This is due to the fact that adapter matrices A and B in…

Machine Learning · Computer Science 2024-07-08 Soufiane Hayou , Nikhil Ghosh , Bin Yu

We explore the question of how to learn an optimal search strategy within the example of a parking problem where parking opportunities arrive according to an unknown inhomogeneous Poisson process. The optimal policy is a threshold-type…

Machine Learning · Computer Science 2026-03-04 Stefan Ankirchner , Maximilian Philipp Thiel