English
Related papers

Related papers: Lottery Jackpots Exist in Pre-trained Models

200 papers

Sparse shrunk additive models and sparse random feature models have been developed separately as methods to learn low-order functions, where there are few interactions between variables, but neither offers computational efficiency. On the…

Machine Learning · Computer Science 2021-12-09 Yuege Xie , Bobby Shi , Hayden Schaeffer , Rachel Ward

Recognition tasks, such as object recognition and keypoint estimation, have seen widespread adoption in recent years. Most state-of-the-art methods for these tasks use deep networks that are computationally expensive and have huge memory…

Computer Vision and Pattern Recognition · Computer Science 2021-04-20 Sharath Girish , Shishira R. Maiya , Kamal Gupta , Hao Chen , Larry Davis , Abhinav Shrivastava

Convolutional Neural Networks (CNNs) are hard to deploy on edge devices due to its high computation and storage complexities. As a common practice for model compression, network pruning consists of two major categories: unstructured and…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Yuchuan Tian , Hanting Chen , Tianyu Guo , Chao Xu , Yunhe Wang

According to the Strong Lottery Ticket Hypothesis, every sufficiently large neural network with randomly initialized weights contains a sub-network which - still with its random weights - already performs as well for a given task as the…

Neural and Evolutionary Computing · Computer Science 2024-11-08 Philipp Altmann , Julian Schönberger , Maximilian Zorn , Thomas Gabor

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

The Strong Lottery Ticket Hypothesis (SLTH) states that randomly-initialised neural networks likely contain subnetworks that perform well without any training. Although unstructured pruning has been extensively studied in this context, its…

Machine Learning · Computer Science 2026-03-11 Arthur da Cunha , Francesco d'Amore , Emanuele Natale

The lottery ticket hypothesis (LTH) has attracted attention because it can explain why over-parameterized models often show high generalization ability. It is known that when we use iterative magnitude pruning (IMP), which is an algorithm…

Machine Learning · Computer Science 2022-09-29 Keitaro Sakamoto , Issei Sato

Compression of convolutional neural network models has recently been dominated by pruning approaches. A class of previous works focuses solely on pruning the unimportant filters to achieve network compression. Another important direction is…

Computer Vision and Pattern Recognition · Computer Science 2022-10-17 Tariq M. Khan , Syed S. Naqvi , Antonio Robles-Kelly , Erik Meijering

Modern deep learning involves training costly, highly overparameterized networks, thus motivating the search for sparser networks that can still be trained to the same accuracy as the full network (i.e. matching). Iterative magnitude…

Machine Learning · Computer Science 2022-10-07 Mansheej Paul , Feng Chen , Brett W. Larsen , Jonathan Frankle , Surya Ganguli , Gintare Karolina Dziugaite

This work introduces a novel approach to pruning deep learning models by using distilled data. Unlike conventional strategies which primarily focus on architectural or algorithmic optimization, our method reconsiders the role of data in…

Machine Learning · Computer Science 2023-08-10 Luke McDermott , Daniel Cummings

It is widely acknowledged that large and sparse models have higher accuracy than small and dense models under the same model size constraints. This motivates us to train a large model and then remove its redundant neurons or weights by…

Computer Vision and Pattern Recognition · Computer Science 2024-01-12 Jianwei Li , Weizhi Gao , Qi Lei , Dongkuan Xu

The lottery ticket hypothesis (Frankle and Carbin, 2018), states that a randomly-initialized network contains a small subnetwork such that, when trained in isolation, can compete with the performance of the original network. We prove an…

Machine Learning · Computer Science 2020-02-04 Eran Malach , Gilad Yehudai , Shai Shalev-Shwartz , Ohad Shamir

Although sparse training has been successfully used in various resource-limited deep learning tasks to save memory, accelerate training, and reduce inference time, the reliability of the produced sparse models remains unexplored. Previous…

Machine Learning · Computer Science 2023-03-02 Bowen Lei , Ruqi Zhang , Dongkuan Xu , Bani Mallick

Large-scale pretrained models such as LXMERT are becoming popular for learning cross-modal representations on text-image pairs for vision-language tasks. According to the lottery ticket hypothesis, NLP and computer vision models contain…

Computer Vision and Pattern Recognition · Computer Science 2023-10-25 Maryam Hashemi , Ghazaleh Mahmoudi , Sara Kodeiri , Hadi Sheikhi , Sauleh Eetemadi

With the remarkable success of deep learning recently, efficient network compression algorithms are urgently demanded for releasing the potential computational power of edge devices, such as smartphones or tablets. However, optimal network…

Computer Vision and Pattern Recognition · Computer Science 2022-02-01 Yuzhang Shang , Bin Duan , Ziliang Zong , Liqiang Nie , Yan Yan

Model pruning seeks to induce sparsity in a deep neural network's various connection matrices, thereby reducing the number of nonzero-valued parameters in the model. Recent reports (Han et al., 2015; Narang et al., 2017) prune deep networks…

Machine Learning · Statistics 2017-11-15 Michael Zhu , Suyog Gupta

Pruning large neural networks to create high-quality, independently trainable sparse masks, which can maintain similar performance to their dense counterparts, is very desirable due to the reduced space and time complexity. As research…

Computer Vision and Pattern Recognition · Computer Science 2022-06-29 Ajay Jaiswal , Haoyu Ma , Tianlong Chen , Ying Ding , Zhangyang Wang

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

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

Large Transformer-based models were shown to be reducible to a smaller number of self-attention heads and layers. We consider this phenomenon from the perspective of the lottery ticket hypothesis, using both structured and magnitude…

Computation and Language · Computer Science 2020-10-27 Sai Prasanna , Anna Rogers , Anna Rumshisky