中文
相关论文

相关论文: KS-Lottery: Finding Certified Lottery Tickets for …

200 篇论文

Current soft prompt methods yield limited performance when applied to small-sized models (fewer than a billion parameters). Deep prompt-tuning, which entails prepending parameters in each layer for enhanced efficacy, presents a solution for…

计算与语言 · 计算机科学 2024-04-02 Mingqi Li , Feng Luo

Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models. However, these…

计算与语言 · 计算机科学 2022-11-15 Rui Zheng , Rong Bao , Yuhao Zhou , Di Liang , Sirui Wang , Wei Wu , Tao Gui , Qi Zhang , Xuanjing Huang

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 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

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

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…

计算机视觉与模式识别 · 计算机科学 2021-12-16 Zhe Gan , Yen-Chun Chen , Linjie Li , Tianlong Chen , Yu Cheng , Shuohang Wang , Jingjing Liu , Lijuan Wang , Zicheng Liu

Consistently scaling pre-trained language models (PLMs) imposes substantial burdens on model adaptation, necessitating more efficient alternatives to conventional fine-tuning. Given the advantage of prompting in the zero-shot setting and…

计算与语言 · 计算机科学 2023-06-01 Yulin Chen , Ning Ding , Xiaobin Wang , Shengding Hu , Hai-Tao Zheng , Zhiyuan Liu , Pengjun Xie

Motivated by reducing the computational and storage costs of LLMs, model compression and KV cache compression have attracted much attention from researchers. However, current methods predominantly emphasize maintaining the performance of…

机器学习 · 计算机科学 2025-02-26 Zhenheng Tang , Xiang Liu , Qian Wang , Peijie Dong , Bingsheng He , Xiaowen Chu , Bo Li

The strong lottery ticket hypothesis (SLTH) conjectures that high-performing subnetworks, called strong lottery tickets (SLTs), are hidden in randomly initialized neural networks. Although recent theoretical studies have established the…

机器学习 · 计算机科学 2025-11-07 Hikari Otsuka , Daiki Chijiwa , Yasuyuki Okoshi , Daichi Fujiki , Susumu Takeuchi , Masato Motomura

The Lottery Ticket Hypothesis (LTH) suggests that over-parameterized neural networks contain sparse subnetworks ("winning tickets") capable of matching full model performance when trained from scratch. With the growing reliance on…

机器学习 · 计算机科学 2025-12-30 Hamed Damirchi , Cristian Rodriguez-Opazo , Ehsan Abbasnejad , Zhen Zhang , Javen Shi

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

Recently, Frankle & Carbin (2019) demonstrated that randomly-initialized dense networks contain subnetworks that once found can be trained to reach test accuracy comparable to the trained dense network. However, finding these high…

机器学习 · 计算机科学 2021-03-18 James Diffenderfer , Bhavya Kailkhura

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…

计算机视觉与模式识别 · 计算机科学 2021-04-20 Sharath Girish , Shishira R. Maiya , Kamal Gupta , Hao Chen , Larry Davis , Abhinav Shrivastava

Quantum computing is an emerging field in computer science that has seen considerable progress in recent years, especially in machine learning. By harnessing the principles of quantum physics, it can surpass the limitations of classical…

The observation of sparse trainable sub-networks within over-parametrized networks - also known as Lottery Tickets (LTs) - has prompted inquiries around their trainability, scaling, uniqueness, and generalization properties. Across 28…

机器学习 · 计算机科学 2020-07-09 Michela Paganini , Jessica Zosa Forde

Lottery Ticket Hypothesis (LTH) raises keen attention to identifying sparse trainable subnetworks, or winning tickets, which can be trained in isolation to achieve similar or even better performance compared to the full models. Despite many…

计算机视觉与模式识别 · 计算机科学 2021-10-29 Xiaohan Chen , Yu Cheng , Shuohang Wang , Zhe Gan , Jingjing Liu , Zhangyang Wang

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 Lottery Ticket Hypothesis suggests that an over-parametrized network consists of ``lottery tickets'', and training a certain collection of them (i.e., a subnetwork) can match the performance of the full model. In this paper, we study…

机器学习 · 计算机科学 2021-06-09 Chen Liang , Simiao Zuo , Minshuo Chen , Haoming Jiang , Xiaodong Liu , Pengcheng He , Tuo Zhao , Weizhu Chen

There have been long-standing controversies and inconsistencies over the experiment setup and criteria for identifying the "winning ticket" in literature. To reconcile such, we revisit the definition of lottery ticket hypothesis, with…

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
‹ 上一页 1 2 3 10 下一页 ›