English
Related papers

Related papers: Sparse Training from Random Initialization: Aligni…

200 papers

Finding neural network weights that generalize well from small datasets is difficult. A promising approach is to learn a weight initialization such that a small number of weight changes results in low generalization error. We show that this…

Deep neural networks often suffer from poor generalization due to complex and non-convex loss landscapes. Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of…

Artificial Intelligence · Computer Science 2023-07-03 Peng Mi , Li Shen , Tianhe Ren , Yiyi Zhou , Tianshuo Xu , Xiaoshuai Sun , Tongliang Liu , Rongrong Ji , Dacheng Tao

During typical gradient-based training of deep neural networks, all of the model's parameters are updated at each iteration. Recent work has shown that it is possible to update only a small subset of the model's parameters during training,…

Machine Learning · Computer Science 2021-11-19 Yi-Lin Sung , Varun Nair , Colin Raffel

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…

Machine Learning · Computer Science 2021-02-01 Neha Mukund Kalibhat , Yogesh Balaji , Soheil Feizi

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…

Machine Learning · Computer Science 2022-06-08 Jonas Fischer , Rebekka Burkholz

Sparse feature selection is necessary when we fit statistical models, we have access to a large group of features, don't know which are relevant, but assume that most are not. Alternatively, when the number of features is larger than the…

Applications · Statistics 2017-04-04 Emiliano Diaz

We propose a new approach for metric learning by framing it as learning a sparse combination of locally discriminative metrics that are inexpensive to generate from the training data. This flexible framework allows us to naturally derive…

Machine Learning · Computer Science 2019-01-25 Yuan Shi , Aurélien Bellet , Fei Sha

Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse…

Neural and Evolutionary Computing · Computer Science 2019-06-28 Shiwei Liu , Decebal Constantin Mocanu , Mykola Pechenizkiy

Deep neural networks are effective feature extractors but they are prohibitively large for deployment scenarios. Due to the huge number of parameters, interpretability of parameters in different layers is not straight-forward. This is why…

Computation and Language · Computer Science 2021-12-23 Saeed Damadi

Dynamic Sparse Training (DST) methods train neural networks by maintaining sparsity while dynamically adapting the network topology. Despite the promise of reduced computation, DST methods converge significantly slower than dense training,…

Machine Learning · Computer Science 2026-05-28 Mohammed Adnan , Rohan Jain , Tom Jacobs , Ekansh Sharma , Rahul G. Krishnan , Rebekka Burkholz , Yani Ioannou

Recent works on sparse neural network training (sparse training) have shown that a compelling trade-off between performance and efficiency can be achieved by training intrinsically sparse neural networks from scratch. Existing sparse…

Machine Learning · Computer Science 2022-08-22 Lu Yin , Vlado Menkovski , Meng Fang , Tianjin Huang , Yulong Pei , Mykola Pechenizkiy , Decebal Constantin Mocanu , Shiwei Liu

While large language models (LLMs) have achieved remarkable performance across a wide range of tasks, their massive scale incurs prohibitive computational and memory costs for pre-training from scratch. Recent studies have investigated the…

Machine Learning · Computer Science 2025-08-05 Jiaxi Li , Lu Yin , Li Shen , Jinjin Xu , Liwu Xu , Tianjin Huang , Wenwu Wang , Shiwei Liu , Xilu Wang

We analyse the pruning procedure behind the lottery ticket hypothesis arXiv:1803.03635v5, iterative magnitude pruning (IMP), when applied to linear models trained by gradient flow. We begin by presenting sufficient conditions on the…

Machine Learning · Computer Science 2021-07-06 Bryn Elesedy , Varun Kanade , Yee Whye Teh

It is now well understood that (1) it is possible to reconstruct sparse signals exactly from what appear to be highly incomplete sets of linear measurements and (2) that this can be done by constrained L1 minimization. In this paper, we…

Methodology · Statistics 2007-11-13 Emmanuel J. Candes , Michael B. Wakin , Stephen P. Boyd

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

Grokking is an intriguing phenomenon of delayed generalization, where neural networks initially memorize training data with perfect accuracy but exhibit poor generalization, subsequently transitioning to a generalizing solution with…

Machine Learning · Computer Science 2025-05-12 Gouki Minegishi , Yusuke Iwasawa , Yutaka Matsuo

Low-rank and sparse composite approximation is a natural idea to compress Large Language Models (LLMs). However, such an idea faces two primary challenges that adversely affect the performance of existing methods. The first challenge…

Machine Learning · Computer Science 2026-02-27 Changhai Zhou , Qian Qiao , Yuhua Zhou , Yuxin Wu , Shichao Weng , Weizhong Zhang , Cheng Jin

Fine-tuning the entire set of parameters of a large pretrained model has become the mainstream approach for transfer learning. To increase its efficiency and prevent catastrophic forgetting and interference, techniques like adapters and…

Computation and Language · Computer Science 2023-02-10 Alan Ansell , Edoardo Maria Ponti , Anna Korhonen , Ivan Vulić

Generalization in deep neural networks remains only partially understood. Inspired by the stronger generalization tendency of biological systems, we explore the hypothesis that robust internal representations should remain effective across…

Machine Learning · Computer Science 2026-03-04 Haotian Wang

Deep neural networks often suffer from poor generalization caused by complex and non-convex loss landscapes. One of the popular solutions is Sharpness-Aware Minimization (SAM), which smooths the loss landscape via minimizing the maximized…

Machine Learning · Computer Science 2022-10-25 Peng Mi , Li Shen , Tianhe Ren , Yiyi Zhou , Xiaoshuai Sun , Rongrong Ji , Dacheng Tao