English
Related papers

Related papers: The Elastic Lottery Ticket Hypothesis

200 papers

The hypothesis that sub-network initializations (lottery) exist within the initializations of over-parameterized networks, which when trained in isolation produce highly generalizable models, has led to crucial insights into network…

Machine Learning · Statistics 2020-10-01 Bindya Venkatesh , Jayaraman J. Thiagarajan , Kowshik Thopalli , Prasanna Sattigeri

Vision transformers have revolutionized computer vision, but their computational demands present challenges for training and deployment. This paper introduces LOTUS (LOttery Transformers with Ultra Sparsity), a novel method that leverages…

Computer Vision and Pattern Recognition · Computer Science 2024-05-03 Ojasw Upadhyay

Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks.…

Machine Learning · Computer Science 2022-10-18 Chen Liu , Ziqi Zhao , Sabine Süsstrunk , Mathieu Salzmann

Since the pioneering work on the lottery ticket hypothesis for graph neural networks (GNNs) was proposed in Chen et al. (2021), the study on finding graph lottery tickets (GLT) has become one of the pivotal focus in the GNN community,…

Machine Learning · Computer Science 2024-03-18 Hyunjin Seo , Jihun Yun , Eunho Yang

In Federated Learning, model training is performed across multiple computing devices, where only parameters are shared with a common central server without exchanging their data instances. This strategy assumes abundance of resources on…

Machine Learning · Computer Science 2023-09-06 Indrajeet Kumar Sinha , Shekhar Verma , Krishna Pratap Singh

We introduce the Learning Hyperplane Tree (LHT), a novel oblique decision tree model designed for expressive and interpretable classification. LHT fundamentally distinguishes itself through a non-iterative, statistically-driven approach to…

Machine Learning · Computer Science 2025-05-08 Hongyi Li , Jun Xu , William Ward Armstrong

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…

Computation and Language · Computer Science 2024-04-02 Mingqi Li , Feng Luo

This paper presents a novel differentiable method for unstructured weight pruning of deep neural networks. Our learned-threshold pruning (LTP) method learns per-layer thresholds via gradient descent, unlike conventional methods where they…

Machine Learning · Computer Science 2021-03-22 Kambiz Azarian , Yash Bhalgat , Jinwon Lee , Tijmen Blankevoort

Federated learning (FL) enables a neural network (NN) to be trained using privacy-sensitive data on mobile devices while retaining all the data on their local storages. However, FL asks the mobile devices to perform heavy communication and…

Networking and Internet Architecture · Computer Science 2022-02-11 Sohei Itahara , Takayuki Nishio , Masahiro Morikura , Koji Yamamoto

Successful adoption of deep learning (DL) in the wild requires models to be: (1) compact, (2) accurate, and (3) robust to distributional shifts. Unfortunately, efforts towards simultaneously meeting these requirements have mostly been…

Machine Learning · Computer Science 2021-11-09 James Diffenderfer , Brian R. Bartoldson , Shreya Chaganti , Jize Zhang , Bhavya Kailkhura

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…

Machine Learning · Computer Science 2021-10-28 Xiaolong Ma , Geng Yuan , Xuan Shen , Tianlong Chen , Xuxi Chen , Xiaohan Chen , Ning Liu , Minghai Qin , Sijia Liu , Zhangyang Wang , Yanzhi Wang

Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which states that competitive smooth (non-binary) subnetworks exist within a dense network in continual learning tasks, we investigate two proposed architecture-based continual…

Machine Learning · Computer Science 2023-03-28 Haeyong Kang , Jaehong Yoon , Sultan Rizky Madjid , Sung Ju Hwang , Chang D. Yoo

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

Network pruning has been known to produce compact models without much accuracy degradation. However, how the pruning process affects a network's robustness and the working mechanism behind remain unresolved. In this work, we theoretically…

Machine Learning · Computer Science 2022-07-13 Shufan Wang , Ningyi Liao , Liyao Xiang , Nanyang Ye , Quanshi Zhang

Although sparse neural networks have been studied extensively, the focus has been primarily on accuracy. In this work, we focus instead on network structure, and analyze three popular algorithms. We first measure performance when structure…

Machine Learning · Computer Science 2020-12-02 Maxwell Van Gelder , Mitchell Wortsman , Kiana Ehsani

The success of lottery ticket initializations (Frankle and Carbin, 2019) suggests that small, sparsified networks can be trained so long as the network is initialized appropriately. Unfortunately, finding these "winning ticket"…

Machine Learning · Statistics 2019-10-29 Ari S. Morcos , Haonan Yu , Michela Paganini , Yuandong Tian

Recent advances in artificial intelligence have relied heavily on increasingly large neural networks, raising concerns about their computational and environmental costs. This paper investigates whether simpler, sparser networks can maintain…

Machine Learning · Computer Science 2025-11-04 C. Díaz-Faloh , R. Mulet

Many applications require sparse neural networks due to space or inference time restrictions. There is a large body of work on training dense networks to yield sparse networks for inference, but this limits the size of the largest trainable…

Machine Learning · Computer Science 2021-07-26 Utku Evci , Trevor Gale , Jacob Menick , Pablo Samuel Castro , Erich Elsen

A key generative principle within social and other complex networks is transitivity, where friends of friends are more likely friends. We propose a new model for highly dense complex networks based on transitivity, called the Iterated Local…

Social and Information Networks · Computer Science 2023-01-24 Anthony Bonato , Ketan Chaudhary

The success of deep ensembles on improving predictive performance, uncertainty estimation, and out-of-distribution robustness has been extensively studied in the machine learning literature. Albeit the promising results, naively training…