English
Related papers

Related papers: GradES: Significantly Faster Training in Transform…

200 papers

Training on edge devices enables personalized model fine-tuning to enhance real-world performance and maintain data privacy. However, the gradient computation for backpropagation in the training requires significant memory buffers to store…

Hardware Architecture · Computer Science 2025-03-25 I-Hsuan Li , Tian-Sheuan Chang

Training deep learning models on embedded devices is typically avoided since this requires more memory, computation and power over inference. In this work, we focus on lowering the amount of memory needed for storing all activations, which…

Computer Vision and Pattern Recognition · Computer Science 2020-09-22 Robby Neven , Marian Verhelst , Tinne Tuytelaars , Toon Goedemé

The remarkable capability of Transformers to do reasoning and few-shot learning, without any fine-tuning, is widely conjectured to stem from their ability to implicitly simulate a multi-step algorithms -- such as gradient descent -- with…

Machine Learning · Computer Science 2024-10-14 Khashayar Gatmiry , Nikunj Saunshi , Sashank J. Reddi , Stefanie Jegelka , Sanjiv Kumar

Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately account for variations in prompt difficulty or rely on…

Machine Learning · Computer Science 2026-03-24 Yongcheng Zeng , Zexu Sun , Bokai Ji , Erxue Min , Hengyi Cai , Shuaiqiang Wang , Dawei Yin , Haifeng Zhang , Xu Chen , Jun Wang

Training instability in modern deep learning systems is frequently triggered by rare but extreme gradient-norm spikes, which can induce oversized parameter updates, corrupt optimizer state, and lead to slow recovery or divergence. Widely…

We introduce new methods for 1) accelerating and 2) stabilizing training for large language-vision models. 1) For acceleration, we introduce SwitchBack, a linear layer for int8 quantized training which provides a speed-up of 13-25% while…

Machine Learning · Computer Science 2023-10-18 Mitchell Wortsman , Tim Dettmers , Luke Zettlemoyer , Ari Morcos , Ali Farhadi , Ludwig Schmidt

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Machine Learning · Computer Science 2020-10-27 Minjia Zhang , Yuxiong He

Transformer models have emerged as fundamental tools across various scientific and engineering disciplines, owing to their outstanding performance in diverse applications. Despite this empirical success, the theoretical foundations of…

Machine Learning · Computer Science 2026-04-14 Zhen Qin , Jinxin Zhou , Jiachen Jiang , Zhihui Zhu

This work, based on Random Matrix Theory (RMT), introduces a novel early-stopping strategy for Transformer training dynamics. Utilizing the Power Law (PL) fit to tansformer attention matrices as a probe, we demarcate training into three…

Machine Learning · Computer Science 2025-12-30 Jing He , Hua Jiang , Cheng Li , Siqian Xin , Shuzhen Yang

Recent developments in large language models have sparked interest in efficient pretraining methods. Stagewise training approaches to improve efficiency, like gradual stacking and layer dropping (Reddi et al, 2023; Zhang & He, 2020), have…

Computation and Language · Computer Science 2024-10-15 Abhishek Panigrahi , Nikunj Saunshi , Kaifeng Lyu , Sobhan Miryoosefi , Sashank Reddi , Satyen Kale , Sanjiv Kumar

Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies reveal significant redundancy in LLMs layers, making layer pruning an active research…

Computation and Language · Computer Science 2026-02-17 Hao Liu , Guangyan Li , Wensheng Zhang , Yongqiang Tang

Full-parameter fine-tuning of large language models is constrained by substantial GPU memory requirements. Low-rank adaptation methods mitigate this challenge by updating only a subset of parameters. However, these approaches often limit…

Computation and Language · Computer Science 2026-04-10 Kaiyuan Tian , Yu Tang , Gongqingjian Jiang , Baihui Liu , Yifu Gao , Xialin Su , Linbo Qiao , Dongsheng Li

Central to the success of Transformers is the attention block, which effectively models global dependencies among input tokens associated to a dataset. However, we theoretically demonstrate that standard attention mechanisms in transformers…

Machine Learning · Computer Science 2026-03-31 Hemanth Saratchandran

Time-sensitive machine learning benefits from Sequential Probability Ratio Test (SPRT), which provides an optimal stopping time for early classification of time series. However, in finite horizon scenarios, where input lengths are finite,…

Machine Learning · Computer Science 2025-01-31 Akinori F. Ebihara , Taiki Miyagawa , Kazuyuki Sakurai , Hitoshi Imaoka

Despite the extensive literature on training loss functions, the evaluation of generalization on the validation set remains underexplored. In this work, we conduct a systematic empirical and statistical study of how the validation criterion…

Machine Learning · Computer Science 2026-02-26 Andrea Apicella , Francesco Isgrò , Andrea Pollastro , Roberto Prevete

Deep neural networks have yielded superior performance in many applications; however, the gradient computation in a deep model with millions of instances lead to a lengthy training process even with modern GPU/TPU hardware acceleration. In…

Machine Learning · Computer Science 2019-05-10 Jiong Zhang , Hsiang-fu Yu , Inderjit S. Dhillon

This paper presents a gradient-informed fine-tuning method for large language models under few-shot conditions. The goal is to enhance task adaptability and training stability when data is limited. The method builds on a base loss function…

Computation and Language · Computer Science 2025-06-03 Hongye Zheng , Yichen Wang , Ray Pan , Guiran Liu , Binrong Zhu , Hanlu Zhang

We study two procedures (reverse-mode and forward-mode) for computing the gradient of the validation error with respect to the hyperparameters of any iterative learning algorithm such as stochastic gradient descent. These procedures mirror…

Machine Learning · Statistics 2017-12-13 Luca Franceschi , Michele Donini , Paolo Frasconi , Massimiliano Pontil

Models such as VGGT and $\pi^3$ have shown strong multi-view 3D performance, but their heavy reliance on global self-attention results in high computational cost. Existing sparse-attention variants offer partial speedups, yet lack a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Xianbing Sun , Zhikai Zhu , Zhengyu Lou , Bo Yang , Jinyang Tang , Liqing Zhang , He Wang , Jianfu Zhang

Innovations in neural architectures have fostered significant breakthroughs in language modeling and computer vision. Unfortunately, novel architectures often result in challenging hyper-parameter choices and training instability if the…

Machine Learning · Computer Science 2021-11-25 Chen Zhu , Renkun Ni , Zheng Xu , Kezhi Kong , W. Ronny Huang , Tom Goldstein