中文
相关论文

相关论文: Plant 'n' Seek: Can You Find the Winning Ticket?

200 篇论文

Neural network pruning techniques can reduce the parameter counts of trained networks by over 90%, decreasing storage requirements and improving computational performance of inference without compromising accuracy. However, contemporary…

机器学习 · 计算机科学 2019-03-05 Jonathan Frankle , Michael Carbin

The search for efficient, sparse deep neural network models is most prominently performed by pruning: training a dense, overparameterized network and removing parameters, usually via following a manually-crafted heuristic. Additionally, the…

机器学习 · 计算机科学 2021-01-12 Pedro Savarese , Hugo Silva , Michael Maire

Spiking Neural Networks (SNNs), a novel brain-inspired algorithm, are garnering increased attention for their superior computation and energy efficiency over traditional artificial neural networks (ANNs). To facilitate deployment on…

神经与进化计算 · 计算机科学 2023-11-22 Hao Cheng , Jiahang Cao , Erjia Xiao , Mengshu Sun , Le Yang , Jize Zhang , Xue Lin , Bhavya Kailkhura , Kaidi Xu , Renjing Xu

Discovering a high-performing sparse network within a massive neural network is advantageous for deploying them on devices with limited storage, such as mobile phones. Additionally, model explainability is essential to fostering trust in…

计算机视觉与模式识别 · 计算机科学 2023-07-27 Shantanu Ghosh , Kayhan Batmanghelich

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…

机器学习 · 计算机科学 2019-12-06 Justin Cosentino , Federico Zaiter , Dan Pei , Jun Zhu

Sparse models require less memory for storage and enable a faster inference by reducing the necessary number of FLOPs. This is relevant both for time-critical and on-device computations using neural networks. The stabilized lottery ticket…

机器学习 · 计算机科学 2020-07-06 Christopher Brix , Parnia Bahar , Hermann Ney

Lottery ticket hypothesis for deep neural networks emphasizes the importance of initialization used to re-train the sparser networks obtained using the iterative magnitude pruning process. An explanation for why the specific initialization…

机器学习 · 计算机科学 2024-06-26 Tausifa Jan Saleem , Ramanjit Ahuja , Surendra Prasad , Brejesh Lall

The lottery ticket hypothesis states that sparse subnetworks exist in randomly initialized dense networks that can be trained to the same accuracy as the dense network they reside in. However, the subsequent work has failed to replicate…

机器学习 · 计算机科学 2021-06-15 Jaron Maene , Mingxiao Li , Marie-Francine Moens

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

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…

计算机视觉与模式识别 · 计算机科学 2022-12-19 Sangyeop Yeo , Yoojin Jang , Jy-yong Sohn , Dongyoon Han , Jaejun Yoo

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…

机器学习 · 计算机科学 2021-12-17 Robert Bain

The lottery ticket hypothesis (LTH) reveals the existence of winning tickets (sparse but critical subnetworks) for dense networks, that can be trained in isolation from random initialization to match the latter's accuracies. However,…

机器学习 · 计算机科学 2021-06-08 Zhenyu Zhang , Xuxi Chen , Tianlong Chen , Zhangyang Wang

The lottery ticket hypothesis (LTH) has shown that dense models contain highly sparse subnetworks (i.e., winning tickets) that can be trained in isolation to match full accuracy. Despite many exciting efforts being made, there is one…

机器学习 · 计算机科学 2022-06-13 Tianlong Chen , Xuxi Chen , Xiaolong Ma , Yanzhi Wang , Zhangyang Wang

Network pruning is a method for reducing test-time computational resource requirements with minimal performance degradation. Conventional wisdom of pruning algorithms suggests that: (1) Pruning methods exploit information from training data…

机器学习 · 计算机科学 2020-10-23 Jingtong Su , Yihang Chen , Tianle Cai , Tianhao Wu , Ruiqi Gao , Liwei Wang , Jason D. Lee

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 postulates that a freshly initialized neural network contains a small subnetwork that can be trained in isolation to achieve similar performance as the full network. Our paper examines several alternatives to…

机器学习 · 计算机科学 2020-06-26 Dániel Lévai , Zsolt Zombori

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

The lottery ticket hypothesis suggests that sparse, sub-networks of a given neural network, if initialized properly, can be trained to reach comparable or even better performance to that of the original network. Prior works in lottery…

机器学习 · 计算机科学 2021-02-01 Neha Mukund Kalibhat , Yogesh Balaji , Soheil Feizi

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

Spiking Neural Networks (SNNs) have recently emerged as a new generation of low-power deep neural networks, which is suitable to be implemented on low-power mobile/edge devices. As such devices have limited memory storage, neural pruning on…

人工智能 · 计算机科学 2022-07-22 Youngeun Kim , Yuhang Li , Hyoungseob Park , Yeshwanth Venkatesha , Ruokai Yin , Priyadarshini Panda
‹ 上一页 1 2 3 10 下一页 ›