English
Related papers

Related papers: Revisit Micro-batch Clipping: Adaptive Data Prunin…

200 papers

The goal of few-shot learning is to generalize and achieve high performance on new unseen learning tasks, where each task has only a limited number of examples available. Gradient-based meta-learning attempts to address this challenging…

Machine Learning · Computer Science 2024-06-13 Christian Raymond , Qi Chen , Bing Xue , Mengjie Zhang

Variance-reduced algorithms, although achieve great theoretical performance, can run slowly in practice due to the periodic gradient estimation with a large batch of data. Batch-size adaptation thus arises as a promising approach to…

Optimization and Control · Mathematics 2020-07-28 Kaiyi Ji , Zhe Wang , Bowen Weng , Yi Zhou , Wei Zhang , Yingbin Liang

Deep learning models require an enormous amount of data for training. However, recently there is a shift in machine learning from model-centric to data-centric approaches. In data-centric approaches, the focus is to refine and improve the…

Computer Vision and Pattern Recognition · Computer Science 2023-08-08 Muhammad Asif Khan , Ridha Hamila , Hamid Menouar

Artificial neural network pruning is a method in which artificial neural network sizes can be reduced while attempting to preserve the predicting capabilities of the network. This is done to make the model smaller or faster during inference…

Machine Learning · Computer Science 2025-05-21 Alexandre Broggi , Nathaniel Bastian , Lance Fiondella , Gokhan Kul

This paper studies the convergence of clipped stochastic gradient descent (SGD) algorithms with decision-dependent data distribution. Our setting is motivated by privacy preserving optimization algorithms that interact with performative…

Optimization and Control · Mathematics 2025-01-31 Qiang Li , Michal Yemini , Hoi-To Wai

Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources…

Computer Vision and Pattern Recognition · Computer Science 2021-12-24 Duo Wang , Salah Karout

In distributed training of deep neural networks, people usually run Stochastic Gradient Descent (SGD) or its variants on each machine and communicate with other machines periodically. However, SGD might converge slowly in training some deep…

Machine Learning · Computer Science 2022-10-14 Mingrui Liu , Zhenxun Zhuang , Yunwei Lei , Chunyang Liao

The current state-of-the-art for few-shot cross-lingual transfer learning first trains on abundant labeled data in the source language and then fine-tunes with a few examples on the target language, termed target-adapting. Though this has…

Computation and Language · Computer Science 2022-05-02 Haoran Xu , Kenton Murray

In recent years, self-supervised contrastive learning has emerged as a distinguished paradigm in the artificial intelligence landscape. It facilitates unsupervised feature learning through contrastive delineations at the instance level.…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Jiansong Zhang , Linlin Shen , Peizhong Liu

Gradient clipping is a fundamental tool in Deep Learning, improving the high-probability convergence of stochastic first-order methods like SGD, AdaGrad, and Adam under heavy-tailed noise, which is common in training large language models.…

Machine Learning · Computer Science 2025-09-30 Saleh Vatan Khah , Savelii Chezhegov , Shahrokh Farahmand , Samuel Horváth , Eduard Gorbunov

Multi-head attention, a collection of several attention mechanisms that independently attend to different parts of the input, is the key ingredient in the Transformer. Recent work has shown, however, that a large proportion of the heads in…

Computation and Language · Computer Science 2023-07-28 Jiaoda Li , Ryan Cotterell , Mrinmaya Sachan

Adam is known to perform significantly better than Stochastic Gradient Descent (SGD) in language models, a phenomenon for which a number of explanations have been proposed. In this work, we revisit this "optimizer gap" through a series of…

Machine Learning · Computer Science 2025-06-17 Teodora Srećković , Jonas Geiping , Antonio Orvieto

Deep pre-trained Transformer models have achieved state-of-the-art results over a variety of natural language processing (NLP) tasks. By learning rich language knowledge with millions of parameters, these models are usually…

Computation and Language · Computer Science 2020-11-10 Zhengyan Zhang , Fanchao Qi , Zhiyuan Liu , Qun Liu , Maosong Sun

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…

Machine Learning · Computer Science 2025-07-18 Suorong Yang , Peijia Li , Yujie Liu , Zhiming Xu , Peng Ye , Wanli Ouyang , Furao Shen , Dongzhan Zhou

Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance gain comes from. In this work, we propose to answer this…

Computation and Language · Computer Science 2022-04-19 Hanjie Chen , Guoqing Zheng , Ahmed Hassan Awadallah , Yangfeng Ji

Large-scale pre-trained models have been remarkably successful in resolving downstream tasks. Nonetheless, deploying these models on low-capability devices still requires an effective approach, such as model pruning. However, pruning the…

Computer Vision and Pattern Recognition · Computer Science 2023-07-11 Haiyan Zhao , Guodong Long

The stochastic gradient descent (SGD) method and its variants are algorithms of choice for many Deep Learning tasks. These methods operate in a small-batch regime wherein a fraction of the training data, say $32$-$512$ data points, is…

Machine Learning · Computer Science 2017-02-13 Nitish Shirish Keskar , Dheevatsa Mudigere , Jorge Nocedal , Mikhail Smelyanskiy , Ping Tak Peter Tang

While it is commonly observed in practice that pruning networks to a certain level of sparsity can improve the quality of the features, a theoretical explanation of this phenomenon remains elusive. In this work, we investigate this by…

Machine Learning · Statistics 2024-06-14 Nuri Mert Vural , Murat A. Erdogdu

Machine learning is increasingly used to guide branch-and-cut (B&C) for mixed-integer linear programming by learning score-based policies for selecting branching variables and cutting planes. Many approaches train on local signals from…

Optimization and Control · Mathematics 2026-02-02 Hongyu Cheng , Amitabh Basu

Large language models often display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drift, amplification of harmful content, and the propagation of unwanted patterns during extended…

Computation and Language · Computer Science 2026-04-24 Afrozah Nadeem , Mark Dras , Usman Naseem