English
Related papers

Related papers: Orthogonal Weight Modification Enhances Learning S…

200 papers

This paper investigates low-rank structure in the gradients of the training loss for two-layer neural networks while relaxing the usual isotropy assumptions on the training data and parameters. We consider a spiked data model in which the…

Machine Learning · Computer Science 2025-10-03 Rishi Sonthalia , Michael Murray , Guido Montúfar

Large Language Models (LLMs) have shown remarkable performance across various tasks, but the escalating demands on computational resources pose significant challenges, particularly in the extensive utilization of full fine-tuning for…

Machine Learning · Computer Science 2025-01-07 Jia-Hong Huang , Yixian Shen , Hongyi Zhu , Stevan Rudinac , Evangelos Kanoulas

Low-Rank Adaptation (LoRA) has emerged as an effective technique for reducing memory overhead in fine-tuning large language models. However, it often suffers from sub-optimal performance compared with full fine-tuning since the update is…

Machine Learning · Computer Science 2025-09-30 Xin Yu , Yujia Wang , Jinghui Chen , Lingzhou Xue

Large multilayer neural networks trained with backpropagation have recently achieved state-of-the-art results in a wide range of problems. However, using backprop for neural net learning still has some disadvantages, e.g., having to tune a…

Machine Learning · Statistics 2015-07-16 José Miguel Hernández-Lobato , Ryan P. Adams

Reinforcement Learning, particularly through policy gradient methods, has played a central role in enabling reasoning capabilities of Large Language Models. However, the optimization stability of policy gradients in this setting remains…

Machine Learning · Computer Science 2026-03-03 Luckeciano C. Melo , Alessandro Abate , Yarin Gal

By and large, Backpropagation (BP) is regarded as one of the most important neural computation algorithms at the basis of the progress in machine learning, including the recent advances in deep learning. However, its computational structure…

Artificial Intelligence · Computer Science 2018-08-22 Alessandro Betti , Marco Gori , Giuseppe Marra

In continual learning (CL), a learner is faced with a sequence of tasks, arriving one after the other, and the goal is to remember all the tasks once the continual learning experience is finished. The prior art in CL uses episodic memory,…

Machine Learning · Computer Science 2020-12-09 Arslan Chaudhry , Naeemullah Khan , Puneet K. Dokania , Philip H. S. Torr

Low-Rank Adaptation (LoRA) enables efficient fine-tuning of large language models but suffers from catastrophic forgetting when learned updates interfere with the dominant singular directions that encode essential pre-trained knowledge. We…

Computation and Language · Computer Science 2025-11-11 Yifeng Xiong , Xiaohui Xie

Preference alignment is pivotal for empowering large language models (LLMs) to generate helpful and harmless responses. However, the performance of preference alignment is highly sensitive to the prevalent noise in the preference data.…

Machine Learning · Computer Science 2024-05-29 Xize Liang , Chao Chen , Shuang Qiu , Jie Wang , Yue Wu , Zhihang Fu , Zhihao Shi , Feng Wu , Jieping Ye

Sequential learning of tasks using gradient descent leads to an unremitting decline in the accuracy of tasks for which training data is no longer available, termed catastrophic forgetting. Generative models have been explored as a means to…

Machine Learning · Computer Science 2020-09-30 Amanda Rios , Laurent Itti

To efficiently train large-scale models, low-bit gradient communication compresses full-precision gradients on local GPU nodes into low-precision ones for higher gradient synchronization efficiency among GPU nodes. However, it often…

Machine Learning · Computer Science 2024-12-02 Xingyu Xie , Zhijie Lin , Kim-Chuan Toh , Pan Zhou

Accelerator memory and networking constraints have emerged as dominant bottlenecks when training large language models LLMs with billions of parameters. Existing low rank gradient estimators such as GaLoRE and FLORA compress gradients and…

Machine Learning · Computer Science 2025-05-27 Matan Haroush , Daniel Soudry

Model compression is a crucial part of deploying neural networks (NNs), especially when the memory and storage of computing devices are limited in many applications. This paper focuses on two model compression techniques: low-rank…

Machine Learning · Computer Science 2024-08-16 Chenyang Li , Jihoon Chung , Mengnan Du , Haimin Wang , Xianlian Zhou , Bo Shen

The advent of large language models (LLMs) has revolutionized natural language processing, enabling unprecedented capabilities in understanding and generating human-like text. However, the computational cost and convergence times associated…

Computation and Language · Computer Science 2024-11-26 Kerim Büyükakyüz

Questions remain on the robustness of data-driven learning methods when crossing the gap from simulation to reality. We utilize weight anchoring, a method known from continual learning, to cultivate and fixate desired behavior in Neural…

Machine Learning · Computer Science 2023-04-21 Steffen Gracla , Edgar Beck , Carsten Bockelmann , Armin Dekorsy

Large language model (LLM) training is often bottlenecked by memory constraints and stochastic gradient noise in extremely high-dimensional parameter spaces. Motivated by empirical evidence that many LLM gradient matrices are effectively…

Machine Learning · Computer Science 2026-03-24 Zehao Li , Tao Ren , Zishi Zhang , Xi Chen , Yijie Peng

The notion of Boolean logic backpropagation was introduced to build neural networks with weights and activations being Boolean numbers. Most of computations can be done with Boolean logic instead of real arithmetic, both during training and…

Machine Learning · Statistics 2024-01-30 Louis Leconte

Large Language Models' (LLMs) weight matrices can often be expressed in low-rank form with potential to relax memory and compute resource requirements. Unlike prior efforts that focus on developing novel matrix decompositions, in this work…

Machine Learning · Computer Science 2025-06-10 Ajay Jaiswal , Yifan Wang , Lu Yin , Shiwei Liu , Runjin Chen , Jiawei Zhao , Ananth Grama , Yuandong Tian , Zhangyang Wang

Low-rank training methods reduce the number of trainable parameters by re-parameterizing the weights with matrix decompositions (e.g., singular value decomposition). However, enforcing a fixed low-rank structure caps the rank of the weight…

Machine Learning · Computer Science 2025-10-16 Hyuntak Shin , Aecheon Jung , Sungeun Hong , Sunwoo Lee

In this paper, we provide a novel analytical perspective on the theoretical understanding of gradient-based learning algorithms by interpreting consensus-based optimization (CBO), a recently proposed multi-particle derivative-free…

Machine Learning · Computer Science 2026-03-02 Konstantin Riedl , Timo Klock , Carina Geldhauser , Massimo Fornasier