English
Related papers

Related papers: LOTUS: Improving Transformer Efficiency with Spars…

200 papers

The \textit{lottery ticket hypothesis} (LTH) states that learning on a properly pruned network (the \textit{winning ticket}) improves test accuracy over the original unpruned network. Although LTH has been justified empirically in a broad…

Machine Learning · Computer Science 2021-12-06 Shuai Zhang , Meng Wang , Sijia Liu , Pin-Yu Chen , Jinjun Xiong

Current state-of-the-art results in Music Information Retrieval are largely dominated by deep learning approaches. These provide unprecedented accuracy across all tasks. However, the consistently overlooked downside of these models is their…

Machine Learning · Computer Science 2020-08-03 Philippe Esling , Theis Bazin , Adrien Bitton , Tristan Carsault , Ninon Devis

Fully exploiting the learning capacity of neural networks requires overparameterized dense networks. On the other side, directly training sparse neural networks typically results in unsatisfactory performance. Lottery Ticket Hypothesis…

Machine Learning · Computer Science 2022-03-09 Yue Bai , Huan Wang , Zhiqiang Tao , Kunpeng Li , Yun Fu

Recent work on deep neural network pruning has shown there exist sparse subnetworks that achieve equal or improved accuracy, training time, and loss using fewer network parameters when compared to their dense counterparts. Orthogonal to…

Machine Learning · Computer Science 2019-12-06 Justin Cosentino , Federico Zaiter , Dan Pei , Jun Zhu

The Vision Transformer architecture is a deep learning model inspired by the success of the Transformer model in Natural Language Processing. However, the self-attention mechanism, large number of parameters, and the requirement for a…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Yogi Prasetyo , Novanto Yudistira , Agus Wahyu Widodo

Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-training sparsity (PTS), which reduces model cost by removing…

Computation and Language · Computer Science 2026-02-26 Minhao Jiang , Zhikai Li , Xuewen Liu , Jing Zhang , Mengjuan Chen , Qingyi Gu

Yes. In this paper, we investigate strong lottery tickets in generative models, the subnetworks that achieve good generative performance without any weight update. Neural network pruning is considered the main cornerstone of model…

Computer Vision and Pattern Recognition · Computer Science 2022-12-19 Sangyeop Yeo , Yoojin Jang , Jy-yong Sohn , Dongyoon Han , Jaejun Yoo

Vision Transformers (ViTs) have computational costs scaling quadratically with the number of tokens, calling for effective token pruning policies. Most existing policies are handcrafted, lacking adaptivity to varying inputs. Moreover, they…

Computer Vision and Pattern Recognition · Computer Science 2025-04-01 Chenglong Lu , Shen Liang , Xuewei Wang , Wei Wang

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challenging and also rarely…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Chong Yu , Tao Chen , Zhongxue Gan , Jiayuan Fan

We introduce TwIST, a distributed training framework for efficient large language model (LLM) sparsification. TwIST trains multiple subnetworks in parallel, periodically aggregates their parameters, and resamples new subnetworks during…

Machine Learning · Computer Science 2025-11-07 Michael Menezes , Barbara Su , Xinze Feng , Yehya Farhat , Hamza Shili , Anastasios Kyrillidis

Fully finetuning foundation language models (LMs) with billions of parameters is often impractical due to high computational costs, memory requirements, and the risk of overfitting. Although methods like low-rank adapters help address these…

Machine Learning · Computer Science 2026-02-11 Jonathan Svirsky , Yehonathan Refael , Ofir Lindenbaum

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

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

Computer Vision and Pattern Recognition · Computer Science 2023-07-07 Xiangcheng Liu , Tianyi Wu , Guodong Guo

Over-parameterized neural networks incur prohibitive memory and computational costs for resource-constrained deployment. The Strong Lottery Ticket (SLT) hypothesis suggests that randomly initialized networks contain sparse subnetworks…

Machine Learning · Computer Science 2026-03-11 Itamar Tsayag , Ofir Lindenbaum

Leveraging attention sparsity to accelerate long-context large language models (LLMs) has been a hot research topic. However, current algorithms such as sparse attention or key-value (KV) cache compression tend to use a fixed budget, which…

Machine Learning · Computer Science 2025-11-05 Chaofan Lin , Jiaming Tang , Shuo Yang , Hanshuo Wang , Tian Tang , Boyu Tian , Ion Stoica , Song Han , Mingyu Gao

The recently proposed Lottery Ticket Hypothesis of Frankle and Carbin (2019) suggests that the performance of over-parameterized deep networks is due to the random initialization seeding the network with a small fraction of favorable…

Machine Learning · Computer Science 2019-12-18 Rahul Mehta

Advancements in Natural Language Processing are heavily reliant on the Transformer architecture, whose improvements come at substantial resource costs due to ever-growing model sizes. This study explores optimization techniques, including…

Machine Learning · Computer Science 2025-02-04 Tom Wallace , Naser Ezzati-Jivan , Beatrice Ombuki-Berman

The underlying loss landscapes of deep neural networks have a great impact on their training, but they have mainly been studied theoretically due to computational constraints. This work vastly reduces the time required to compute such loss…

Machine Learning · Computer Science 2021-12-17 Robert Bain

Large pre-trained transformers have been receiving explosive attention in the past few years, due to their wide adaptability for numerous downstream applications via fine-tuning, but their exponentially increasing parameter counts are…

Machine Learning · Computer Science 2023-06-21 Ajay Jaiswal , Shiwei Liu , Tianlong Chen , Ying Ding , Zhangyang Wang

Vision Transformers (ViTs) have shown impressive performance in computer vision, but their high computational cost, quadratic in the number of tokens, limits their adoption in computation-constrained applications. However, this large number…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Yifei Liu , Mathias Gehrig , Nico Messikommer , Marco Cannici , Davide Scaramuzza