English
Related papers

Related papers: Lottery Tickets in Linear Models: An Analysis of I…

200 papers

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…

Machine Learning · Computer Science 2020-03-13 Bai Li , Shiqi Wang , Yunhan Jia , Yantao Lu , Zhenyu Zhong , Lawrence Carin , Suman Jana

It is widely acknowledged that large and sparse models have higher accuracy than small and dense models under the same model size constraints. This motivates us to train a large model and then remove its redundant neurons or weights by…

Computer Vision and Pattern Recognition · Computer Science 2024-01-12 Jianwei Li , Weizhi Gao , Qi Lei , Dongkuan Xu

Empirical networks of weighted dyadic relations often contain noisy edges that alter the global characteristics of the network and obfuscate the most important structures therein. Graph pruning is the process of identifying the most…

Physics and Society · Physics 2016-01-20 Navid Dianati

The lottery ticket hypothesis posits the existence of ``winning tickets'' within a randomly initialized neural network. Do winning tickets exist for LLMs in fine-tuning scenarios? How can we find such winning tickets? In this paper, we…

Computation and Language · Computer Science 2024-06-04 Fei Yuan , Chang Ma , Shuai Yuan , Qiushi Sun , Lei Li

The adoption of Foundation Models in resource-constrained environments remains challenging due to their large size and inference costs. A promising way to overcome these limitations is post-training compression, which aims to balance…

Inductive logic programming (ILP) is a form of logical machine learning. Most ILP algorithms learn a single hypothesis from a single training run. Ensemble methods train an ILP algorithm multiple times to learn multiple hypotheses. In this…

Machine Learning · Computer Science 2025-10-29 Mingyue Liu , Andrew Cropper

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

The marginal likelihood is a well established model selection criterion in Bayesian statistics. It also allows to efficiently calculate the marginal posterior model probabilities that can be used for Bayesian model averaging of quantities…

Computation · Statistics 2016-11-07 Aliaksandr Hubin , Geir Storvik

Consider a fair lottery over the natural numbers in which the selected number is removed. This lottery is iterated countably infinite times, with a known ratio of iterations to natural numbers. Removed numbers are not replaced. The natural…

Combinatorics · Mathematics 2024-09-09 Enciso-Alva , Julio Cesar

We show that the error of iteratively magnitude-pruned networks empirically follows a scaling law with interpretable coefficients that depend on the architecture and task. We functionally approximate the error of the pruned networks,…

Machine Learning · Computer Science 2021-07-06 Jonathan S. Rosenfeld , Jonathan Frankle , Michael Carbin , Nir Shavit

Many Neural Network Pruning approaches consist of several iterative training and pruning steps, seemingly losing a significant amount of their performance after pruning and then recovering it in the subsequent retraining phase. Recent works…

Machine Learning · Computer Science 2023-03-14 Max Zimmer , Christoph Spiegel , Sebastian Pokutta

Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in…

Computer Vision and Pattern Recognition · Computer Science 2020-08-17 Duong H. Le , Trung-Nhan Vo , Nam Thoai

We introduce Probe Pruning (PP), a novel framework for online, dynamic, structured pruning of Large Language Models (LLMs) applied in a batch-wise manner. PP leverages the insight that not all samples and tokens contribute equally to the…

Computation and Language · Computer Science 2025-02-24 Qi Le , Enmao Diao , Ziyan Wang , Xinran Wang , Jie Ding , Li Yang , Ali Anwar

We describe here an iterative method for jointly estimating the noise power spectrum from a scanning experiment's time-ordered data, together with the maximum-likelihood map. We test the robustness of this method on simulated datasets with…

Astrophysics · Physics 2007-05-23 S. Prunet , C. B. Netterfield , E. Hivon , B. P. Crill

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…

Computer Vision and Pattern Recognition · Computer Science 2021-12-16 Zhe Gan , Yen-Chun Chen , Linjie Li , Tianlong Chen , Yu Cheng , Shuohang Wang , Jingjing Liu , Lijuan Wang , Zicheng Liu

Randomly initialized dense networks contain subnetworks that achieve high accuracy without weight learning--strong lottery tickets (SLTs). Recently, Gadhikar et al. (2023) demonstrated that SLTs could also be found within a randomly pruned…

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

Inductive logic programming (ILP) is a form of logical machine learning. The goal is to search a hypothesis space for a hypothesis that generalises training examples and background knowledge. We introduce an approach that 'shrinks' the…

Artificial Intelligence · Computer Science 2026-05-18 Andrew Cropper , Filipe Gouveia , David M. Cerna

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…

Machine Learning · Statistics 2020-02-27 Haonan Yu , Sergey Edunov , Yuandong Tian , Ari S. Morcos

Inductive Logic Programming (ILP) combines rule-based and statistical artificial intelligence methods, by learning a hypothesis comprising a set of rules given background knowledge and constraints for the search space. We focus on extending…

Artificial Intelligence · Computer Science 2018-02-01 Mishal Kazmi , Peter Schüller , Yücel Saygın