中文
相关论文

相关论文: Sanity Checks for Lottery Tickets: Does Your Winni…

200 篇论文

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…

机器学习 · 计算机科学 2024-03-14 Bohan Liu , Zijie Zhang , Peixiong He , Zhensen Wang , Yang Xiao , Ruimeng Ye , Yang Zhou , Wei-Shinn Ku , Bo Hui

The recent lottery ticket hypothesis proposes that there is one sub-network that matches the accuracy of the original network when trained in isolation. We show that instead each network contains several winning tickets, even if the initial…

机器学习 · 计算机科学 2020-06-15 Kathrin Grosse , Michael Backes

The lottery ticket hypothesis proposes that over-parameterization of deep neural networks (DNNs) aids training by increasing the probability of a "lucky" sub-network initialization being present rather than by helping the optimization…

机器学习 · 统计学 2020-02-27 Haonan Yu , Sergey Edunov , Yuandong Tian , Ari S. Morcos

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…

机器学习 · 计算机科学 2021-11-02 Xuxi Chen , Tianlong Chen , Zhenyu Zhang , Zhangyang Wang

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…

机器学习 · 计算机科学 2020-02-04 Eran Malach , Gilad Yehudai , Shai Shalev-Shwartz , Ohad Shamir

Recent research has proposed the lottery ticket hypothesis, suggesting that for a deep neural network, there exist trainable sub-networks performing equally or better than the original model with commensurate training steps. While this…

机器学习 · 计算机科学 2020-03-13 Bai Li , Shiqi Wang , Yunhan Jia , Yantao Lu , Zhenyu Zhong , Lawrence Carin , Suman Jana

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…

机器学习 · 计算机科学 2022-03-09 Yue Bai , Huan Wang , Zhiqiang Tao , Kunpeng Li , Yun Fu

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…

机器学习 · 计算机科学 2021-12-06 Shuai Zhang , Meng Wang , Sijia Liu , Pin-Yu Chen , Jinjun Xiong

The proposition of lottery ticket hypothesis revealed the relationship between network structure and initialization parameters and the learning potential of neural networks. The original lottery ticket hypothesis performs pruning and weight…

机器学习 · 计算机科学 2021-09-10 Di Zhang

The lottery ticket hypothesis conjectures the existence of sparse subnetworks of large randomly initialized deep neural networks that can be successfully trained in isolation. Recent work has experimentally observed that some of these…

机器学习 · 计算机科学 2022-03-17 Rebekka Burkholz , Nilanjana Laha , Rajarshi Mukherjee , Alkis Gotovos

In deep model compression, the recent finding "Lottery Ticket Hypothesis" (LTH) (Frankle & Carbin, 2018) pointed out that there could exist a winning ticket (i.e., a properly pruned sub-network together with original weight initialization)…

机器学习 · 计算机科学 2021-07-20 Ning Liu , Geng Yuan , Zhengping Che , Xuan Shen , Xiaolong Ma , Qing Jin , Jian Ren , Jian Tang , Sijia Liu , Yanzhi Wang

The Lottery Ticket Hypothesis suggests large, over-parameterized neural networks consist of small, sparse subnetworks that can be trained in isolation to reach a similar (or better) test accuracy. However, the initialization and…

计算与语言 · 计算机科学 2019-10-29 Shrey Desai , Hongyuan Zhan , Ahmed Aly

Bayesian neural networks (BNNs) are a useful tool for uncertainty quantification, but require substantially more computational resources than conventional neural networks. For non-Bayesian networks, the Lottery Ticket Hypothesis (LTH)…

机器学习 · 计算机科学 2026-02-24 Nicholas Kuhn , Arvid Weyrauch , Lars Heyen , Achim Streit , Markus Götz , Charlotte Debus

Neural architecture search (NAS) has demonstrated amazing success in searching for efficient deep neural networks (DNNs) from a given supernet. In parallel, the lottery ticket hypothesis has shown that DNNs contain small subnetworks that…

计算机视觉与模式识别 · 计算机科学 2025-03-04 Haoran You , Baopu Li , Zhanyi Sun , Xu Ouyang , Yingyan Celine Lin

Recent work on the Lottery Ticket Hypothesis (LTH) shows that there exist ``\textit{winning tickets}'' in large neural networks. These tickets represent ``sparse'' versions of the full model that can be trained independently to achieve…

机器学习 · 计算机科学 2022-10-31 Qihan Wang , Chen Dun , Fangshuo Liao , Chris Jermaine , Anastasios Kyrillidis

The Lottery Ticket Hypothesis (LTH) states that for a reasonably sized neural network, a sub-network within the same network yields no less performance than the dense counterpart when trained from the same initialization. This work…

机器学习 · 计算机科学 2022-06-17 Surya Kant Sahu , Sai Mitheran , Somya Suhans Mahapatra

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…

机器学习 · 计算机科学 2026-05-19 Alon Bebchuk , Nir Shavit

Building modern deep learning systems that are not just effective but also efficient requires rethinking established paradigms for model training and neural architecture design. Instead of adapting highly overparameterized networks and…

机器学习 · 计算机科学 2025-08-13 Julian Schönberger , Maximilian Zorn , Jonas Nüßlein , Thomas Gabor , Philipp Altmann

The lottery ticket hypothesis has sparked the rapid development of pruning algorithms that aim to reduce the computational costs associated with deep learning during training and model deployment. Currently, such algorithms are primarily…

机器学习 · 计算机科学 2022-06-08 Jonas Fischer , Rebekka Burkholz

Lottery Ticket Hypothesis (LTH) suggests that a dense neural network contains a sparse sub-network that can match the performance of the original dense network when trained in isolation from scratch. Most works retrain the sparse…

机器学习 · 计算机科学 2021-10-12 Ajay Kumar Jaiswal , Haoyu Ma , Tianlong Chen , Ying Ding , Zhangyang Wang
‹ 上一页 1 2 3 10 下一页 ›