English
Related papers

Related papers: Is Flash Attention Stable?

200 papers

It is known that training deep neural networks, in particular, deep convolutional networks, with aggressively reduced numerical precision is challenging. The stochastic gradient descent algorithm becomes unstable in the presence of noisy…

Machine Learning · Computer Science 2016-07-11 Darryl D. Lin , Sachin S. Talathi

We empirically demonstrate that full-batch gradient descent on neural network training objectives typically operates in a regime we call the Edge of Stability. In this regime, the maximum eigenvalue of the training loss Hessian hovers just…

Machine Learning · Computer Science 2022-11-24 Jeremy M. Cohen , Simran Kaur , Yuanzhi Li , J. Zico Kolter , Ameet Talwalkar

Multi-Agent Reinforcement Learning involves agents that learn together in a shared environment, leading to emergent dynamics sensitive to initial conditions and parameter variations. A Dynamical Systems approach, which studies the evolution…

Multiagent Systems · Computer Science 2025-01-03 David Goll , Jobst Heitzig , Wolfram Barfuss

Large batch size training of Neural Networks has been shown to incur accuracy loss when trained with the current methods. The exact underlying reasons for this are still not completely understood. Here, we study large batch size training…

Computer Vision and Pattern Recognition · Computer Science 2021-04-21 Zhewei Yao , Amir Gholami , Qi Lei , Kurt Keutzer , Michael W. Mahoney

As deep neural networks are highly expressive, it is important to find solutions with small generalization gap (the difference between the performance on the training data and unseen data). Focusing on the stochastic nature of training, we…

Machine Learning · Computer Science 2023-10-31 Rie Johnson , Tong Zhang

Training Deep Neural Networks (DNNs) is still highly time-consuming and compute-intensive. It has been shown that adapting a pretrained model may significantly accelerate this process. With a focus on classification, we show that current…

Neural and Evolutionary Computing · Computer Science 2020-12-01 Farshid Varno , Lucas May Petry , Lisa Di Jorio , Stan Matwin

In asynchronous federated learning (FL), client devices send updates to a central server at varying times based on their computational speed, often using stale versions of the global model. This staleness can degrade the convergence and…

Machine Learning · Computer Science 2026-03-10 Patrick Wilhelm , Odej Kao

Stance Detection (StD) aims to detect an author's stance towards a certain topic or claim and has become a key component in applications like fake news detection, claim validation, and argument search. However, while stance is easily…

Computation and Language · Computer Science 2020-01-07 Benjamin Schiller , Johannes Daxenberger , Iryna Gurevych

This letter presents a high-dimensional analysis of the training dynamics for a single-layer nonlinear contrastive learning model. The empirical distribution of the model weights converges to a deterministic measure governed by a…

Machine Learning · Computer Science 2024-06-12 Lineghuan Meng , Chuang Wang

The same machine learning model running on different edge devices may produce highly-divergent outputs on a nearly-identical input. Possible reasons for the divergence include differences in the device sensors, the device's signal…

Machine Learning · Computer Science 2020-10-20 Eyal Cidon , Evgenya Pergament , Zain Asgar , Asaf Cidon , Sachin Katti

The multi-stage phenomenon in the training loss curves of neural networks has been widely observed, reflecting the non-linearity and complexity inherent in the training process. In this work, we investigate the training dynamics of neural…

Machine Learning · Computer Science 2024-11-07 Zheng-An Chen , Tao Luo , GuiHong Wang

Generative data augmentation, which scales datasets by obtaining fake labeled examples from a trained conditional generative model, boosts classification performance in various learning tasks including (semi-)supervised learning, few-shot…

Machine Learning · Computer Science 2023-05-30 Chenyu Zheng , Guoqiang Wu , Chongxuan Li

Adversarial attacks against deep learning models have gained significant attention and recent works have proposed explanations for the existence of adversarial examples and techniques to defend the models against these attacks. Attention in…

Computer Vision and Pattern Recognition · Computer Science 2021-09-03 Prachi Agrawal , Narinder Singh Punn , Sanjay Kumar Sonbhadra , Sonali Agarwal

Recently multimodal transformer models have gained popularity because their performance on language and vision tasks suggest they learn rich visual-linguistic representations. Focusing on zero-shot image retrieval tasks, we study three…

Computation and Language · Computer Science 2021-02-02 Lisa Anne Hendricks , John Mellor , Rosalia Schneider , Jean-Baptiste Alayrac , Aida Nematzadeh

Contrastive divergence is a popular method of training energy-based models, but is known to have difficulties with training stability. We propose an adaptation to improve contrastive divergence training by scrutinizing a gradient term that…

Machine Learning · Computer Science 2021-06-14 Yilun Du , Shuang Li , Joshua Tenenbaum , Igor Mordatch

Attention-based neural networks have achieved state-of-the-art results on a wide range of tasks. Most such models use deterministic attention while stochastic attention is less explored due to the optimization difficulties or complicated…

Machine Learning · Computer Science 2021-06-10 Shujian Zhang , Xinjie Fan , Bo Chen , Mingyuan Zhou

Transformers are slow and memory-hungry on long sequences, since the time and memory complexity of self-attention are quadratic in sequence length. Approximate attention methods have attempted to address this problem by trading off model…

Machine Learning · Computer Science 2022-06-24 Tri Dao , Daniel Y. Fu , Stefano Ermon , Atri Rudra , Christopher Ré

Performative prediction is a framework that captures distribution shifts that occur during the training of machine learning models due to their deployment. As the trained model is used, data generation causes the model to evolve, leading to…

Machine Learning · Computer Science 2025-11-10 Xue Zheng , Tian Xie , Xuwei Tan , Aylin Yener , Xueru Zhang

Attention with bias, which extends standard attention by introducing prior knowledge as an additive bias matrix to the query-key scores, has been widely deployed in vision, language, protein-folding and other advanced scientific models,…

Machine Learning · Computer Science 2025-10-27 Haixu Wu , Minghao Guo , Yuezhou Ma , Yuanxu Sun , Jianmin Wang , Wojciech Matusik , Mingsheng Long

Reliability issues stemming from device level non-idealities of non-volatile emerging technologies like ferroelectric field-effect transistors (FeFET), especially at scaled dimensions, cause substantial degradation in the accuracy of…

Emerging Technologies · Computer Science 2024-03-14 Bibhas Manna , Arnob Saha , Zhouhang Jiang , Kai Ni , Abhronil Sengupta