English
Related papers

Related papers: Exploring the Lottery Ticket Hypothesis with Expla…

200 papers

The strong lottery ticket hypothesis has highlighted the potential for training deep neural networks by pruning, which has inspired interesting practical and theoretical insights into how neural networks can represent functions. For…

Machine Learning · Computer Science 2023-01-10 Rebekka Burkholz

The Multi-Prize Lottery Ticket Hypothesis posits that randomly initialized neural networks contain several subnetworks that achieve comparable accuracy to fully trained models of the same architecture. However, current methods require that…

Machine Learning · Computer Science 2023-03-29 Matt Gorbett , Darrell Whitley

Singular-value-decomposition-based coherent integrated photonic neural networks (SC-IPNNs) have a large footprint, suffer from high static power consumption for training and inference, and cannot be pruned using conventional DNN pruning…

Emerging Technologies · Computer Science 2021-12-15 Sanmitra Banerjee , Mahdi Nikdast , Sudeep Pasricha , Krishnendu Chakrabarty

Ensembling is a popular method used to improve performance as a last resort. However, ensembling multiple models finetuned from a single pretrained model has been not very effective; this could be due to the lack of diversity among ensemble…

Machine Learning · Computer Science 2022-05-25 Sosuke Kobayashi , Shun Kiyono , Jun Suzuki , Kentaro Inui

Pruning deep neural networks is a widely used strategy to alleviate the computational burden in machine learning. Overwhelming empirical evidence suggests that pruned models retain very high accuracy even with a tiny fraction of parameters.…

Machine Learning · Computer Science 2023-09-27 Viplove Arora , Daniele Irto , Sebastian Goldt , Guido Sanguinetti

The goal of model compression is to reduce the size of a large neural network while retaining a comparable performance. As a result, computation and memory costs in resource-limited applications may be significantly reduced by dropping…

Machine Learning · Statistics 2022-11-10 Wenjing Yang , Ganghua Wang , Jie Ding , Yuhong Yang

The lottery ticket hypothesis posits that dense networks contain sparse subnetworks, ``winning tickets,'' that, when rewound to their initial weights and retrained in isolation, match the performance of the full model. We ask a more…

Machine Learning · Computer Science 2026-05-19 Alon Bebchuk , Nir Shavit

Pre-training serves as a broadly adopted starting point for transfer learning on various downstream tasks. Recent investigations of lottery tickets hypothesis (LTH) demonstrate such enormous pre-trained models can be replaced by extremely…

Machine Learning · Computer Science 2022-06-13 Tianlong Chen , Zhenyu Zhang , Sijia Liu , Yang Zhang , Shiyu Chang , Zhangyang Wang

With the emergence of the Software 3.0 era, there is a growing trend of compressing and integrating large models into software systems, with significant societal implications. Regrettably, in numerous instances, model compression techniques…

Software Engineering · Computer Science 2024-07-04 Xuanqi Gao , Weipeng Jiang , Juan Zhai , Shiqing Ma , Xiaoyu Zhang , Chao Shen

Neural network pruning is a fruitful area of research with surging interest in high sparsity regimes. Benchmarking in this domain heavily relies on faithful representation of the sparsity of subnetworks, which has been traditionally…

Machine Learning · Computer Science 2023-04-11 Artem Vysogorets , Julia Kempe

Grokking is an intriguing phenomenon of delayed generalization, where neural networks initially memorize training data with perfect accuracy but exhibit poor generalization, subsequently transitioning to a generalizing solution with…

Machine Learning · Computer Science 2025-05-12 Gouki Minegishi , Yusuke Iwasawa , Yutaka Matsuo

Despite the impressive performance of deep neural networks (DNNs), their computational complexity and storage space consumption have led to the concept of network compression. While DNN compression techniques such as pruning and low-rank…

Machine Learning · Computer Science 2025-07-04 Mahsa Mozafari-Nia , Salimeh Yasaei Sekeh

Large neural networks can be pruned to a small fraction of their original size, with little loss in accuracy, by following a time-consuming "train, prune, re-train" approach. Frankle & Carbin conjecture that we can avoid this by training…

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

We argue that many properties of fully-connected feedforward neural networks (FCNNs), also called multi-layer perceptrons (MLPs), are explainable from the analysis of a single pair of operations, namely a random projection into a…

Machine Learning · Computer Science 2022-11-29 Sayandev Mukherjee , Bernardo A. Huberman

In recent years, deep network pruning has attracted significant attention in order to enable the rapid deployment of AI into small devices with computation and memory constraints. Pruning is often achieved by dropping redundant weights,…

Machine Learning · Computer Science 2023-08-24 Enmao Diao , Ganghua Wang , Jiawei Zhan , Yuhong Yang , Jie Ding , Vahid Tarokh

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

The Lottery Ticket hypothesis proposes that ideal, sparse subnetworks, called lottery tickets, exist in untrained dense neural networks. The Early Bird hypothesis proposes an efficient algorithm to find these winning lottery tickets in…

Machine Learning · Computer Science 2024-12-12 Adithya Vasudev

Is the lottery ticket phenomenon an idiosyncrasy of gradient-based training or does it generalize to evolutionary optimization? In this paper we establish the existence of highly sparse trainable initializations for evolution strategies…

Neural and Evolutionary Computing · Computer Science 2023-06-02 Robert Tjarko Lange , Henning Sprekeler

Meta-learning aims to solve unseen tasks with few labelled instances. Nevertheless, despite its effectiveness for quick learning in existing optimization-based methods, it has several flaws. Inconsequential connections are frequently seen…

Machine Learning · Computer Science 2023-04-07 Sambhavi Tiwari , Manas Gogoi , Shekhar Verma , Krishna Pratap Singh