English
Related papers

Related papers: Sparse Transfer Learning via Winning Lottery Ticke…

200 papers

Randomly initialized dense networks contain subnetworks that achieve high accuracy without weight learning--strong lottery tickets (SLTs). Recently, Gadhikar et al. (2023) demonstrated that SLTs could also be found within a randomly pruned…

Network pruning is widely used for reducing the heavy inference cost of deep models in low-resource settings. A typical pruning algorithm is a three-stage pipeline, i.e., training (a large model), pruning and fine-tuning. During pruning,…

Machine Learning · Computer Science 2019-03-06 Zhuang Liu , Mingjie Sun , Tinghui Zhou , Gao Huang , Trevor Darrell

Large pre-trained transformers are show-stealer in modern-day deep learning, and it becomes crucial to comprehend the parsimonious patterns that exist within them as they grow in scale. With exploding parameter counts, Lottery Ticket…

Machine Learning · Computer Science 2023-08-11 Ajay Jaiswal , Shiwei Liu , Tianlong Chen , Zhangyang Wang

Recent studies on the lottery ticket hypothesis (LTH) show that pre-trained language models (PLMs) like BERT contain matching subnetworks that have similar transfer learning performance as the original PLM. These subnetworks are found using…

Computation and Language · Computer Science 2022-05-31 Yuanxin Liu , Fandong Meng , Zheng Lin , Peng Fu , Yanan Cao , Weiping Wang , Jie Zhou

The strong {\it lottery ticket hypothesis} (LTH) postulates that one can approximate any target neural network by only pruning the weights of a sufficiently over-parameterized random network. A recent work by Malach et al.…

Machine Learning · Computer Science 2021-03-12 Ankit Pensia , Shashank Rajput , Alliot Nagle , Harit Vishwakarma , Dimitris Papailiopoulos

A striking observation about iterative magnitude pruning (IMP; Frankle et al. 2020) is that $\unicode{x2014}$ after just a few hundred steps of dense training $\unicode{x2014}$ the method can find a sparse sub-network that can be trained to…

Machine Learning · Computer Science 2022-06-06 Mansheej Paul , Brett W. Larsen , Surya Ganguli , Jonathan Frankle , Gintare Karolina Dziugaite

The Lottery Ticket Hypothesis (LTH) suggests there exists a sparse LTH mask and weights that achieve the same generalization performance as the dense model while using significantly fewer parameters. However, finding a LTH solution is…

Machine Learning · Computer Science 2025-08-18 Mohammed Adnan , Rohan Jain , Ekansh Sharma , Rahul G. Krishnan , Yani Ioannou

The Lottery Ticket Hypothesis suggests that an over-parametrized network consists of ``lottery tickets'', and training a certain collection of them (i.e., a subnetwork) can match the performance of the full model. In this paper, we study…

Machine Learning · Computer Science 2021-06-09 Chen Liang , Simiao Zuo , Minshuo Chen , Haoming Jiang , Xiaodong Liu , Pengcheng He , Tuo Zhao , Weizhu Chen

The Lottery Ticket Hypothesis (LTH) states that a dense neural network model contains a highly sparse subnetwork (i.e., winning tickets) that can achieve even better performance than the original model when trained in isolation. While LTH…

Machine Learning · Computer Science 2024-03-14 Bohan Liu , Zijie Zhang , Peixiong He , Zhensen Wang , Yang Xiao , Ruimeng Ye , Yang Zhou , Wei-Shinn Ku , Bo Hui

Lottery tickets (LTs) is able to discover accurate and sparse subnetworks that could be trained in isolation to match the performance of dense networks. Ensemble, in parallel, is one of the oldest time-proven tricks in machine learning to…

Machine Learning · Computer Science 2023-04-05 Lu Yin , Shiwei Liu , Meng Fang , Tianjin Huang , Vlado Menkovski , Mykola Pechenizkiy

Large-scale pre-training has recently revolutionized vision-and-language (VL) research. Models such as LXMERT and UNITER have significantly lifted the state of the art over a wide range of VL tasks. However, the large number of parameters…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Zhe Gan , Yen-Chun Chen , Linjie Li , Tianlong Chen , Yu Cheng , Shuohang Wang , Jingjing Liu , Lijuan Wang , Zicheng Liu

Recent advances in deepfake technology have created increasingly convincing synthetic media that poses significant challenges to information integrity and social trust. While current detection methods show promise, their underlying…

Computer Vision and Pattern Recognition · Computer Science 2025-07-22 Lisan Al Amin , Md. Ismail Hossain , Thanh Thi Nguyen , Tasnim Jahan , Mahbubul Islam , Faisal Quader

Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets. Generally, more accurate models on the "upstream" dataset tend to…

Computer Vision and Pattern Recognition · Computer Science 2022-04-22 Eugenia Iofinova , Alexandra Peste , Mark Kurtz , Dan Alistarh

Deep neural networks are effective feature extractors but they are prohibitively large for deployment scenarios. Due to the huge number of parameters, interpretability of parameters in different layers is not straight-forward. This is why…

Computation and Language · Computer Science 2021-12-23 Saeed Damadi

The Lottery Ticket Hypothesis (LTH) showed that by iteratively training a model, removing connections with the lowest global weight magnitude and rewinding the remaining connections, sparse networks can be extracted. This global comparison…

Computer Vision and Pattern Recognition · Computer Science 2023-02-23 Benjamin Vandersmissen , Jose Oramas

The Lottery Ticket Hypothesis asserts the existence of highly sparse, trainable subnetworks ('winning tickets') within dense, randomly initialized neural networks. However, state-of-the-art methods of drawing these tickets, like Lottery…

Machine Learning · Computer Science 2025-12-09 Tanay Arora , Christof Teuscher

Pruning methods can considerably reduce the size of artificial neural networks without harming their performance. In some cases, they can even uncover sub-networks that, when trained in isolation, match or surpass the test accuracy of their…

Machine Learning · Computer Science 2021-05-17 Franco Pellegrini , Giulio Biroli

Recent works have shown that Dataset Distillation, the process for summarizing the training data, can be leveraged to accelerate the training of deep learning models. However, its impact on training dynamics, particularly in neural network…

Machine Learning · Computer Science 2025-04-15 Luke McDermott , Rahul Parhi

Despite tremendous success in many application scenarios, the training and inference costs of using deep learning are also rapidly increasing over time. The lottery ticket hypothesis (LTH) emerges as a promising framework to leverage a…

Machine Learning · Computer Science 2021-11-02 Xuxi Chen , Tianlong Chen , Zhenyu Zhang , Zhangyang Wang

People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity. However, our work surprisingly discovers that network pruning sometimes even…

Machine Learning · Computer Science 2022-06-20 Zheng He , Zeke Xie , Quanzhi Zhu , Zengchang Qin