English
Related papers

Related papers: RNN Architecture Learning with Sparse Regularizati…

200 papers

Large language models (LLMs) are trained for downstream tasks by updating their parameters (e.g., via RL). However, updating parameters forces them to absorb task-specific information, which can result in catastrophic forgetting and loss of…

Sparse mapping has been a key methodology in many high-dimensional scientific problems. When multiple tasks share the set of relevant features, learning them jointly in a group drastically improves the quality of relevant feature selection.…

Machine Learning · Statistics 2017-09-18 Meghana Kshirsagar , Eunho Yang , Aurélie C. Lozano

Much work has been done recently to make neural networks more interpretable, and one obvious approach is to arrange for the network to use only a subset of the available features. In linear models, Lasso (or $\ell_1$-regularized) regression…

Machine Learning · Statistics 2021-06-17 Ismael Lemhadri , Feng Ruan , Louis Abraham , Robert Tibshirani

We consider model selection and estimation for partial spline models and propose a new regularization method in the context of smoothing splines. The regularization method has a simple yet elegant form, consisting of roughness penalty on…

Methodology · Statistics 2013-11-25 Guang Cheng , Hao Helen Zhang , Zuofeng Shang

Despite the popularity of deep learning, structure learning for deep models remains a relatively under-explored area. In contrast, structure learning has been studied extensively for probabilistic graphical models (PGMs). In particular, an…

Machine Learning · Computer Science 2018-03-19 Zhourong Chen , Xiaopeng Li , Nevin L. Zhang

Due to the significant computational challenge of training large-scale graph neural networks (GNNs), various sparse learning techniques have been exploited to reduce memory and storage costs. Examples include \textit{graph sparsification}…

Machine Learning · Computer Science 2023-02-07 Shuai Zhang , Meng Wang , Pin-Yu Chen , Sijia Liu , Songtao Lu , Miao Liu

Learning governing equations allows for deeper understanding of the structure and dynamics of data. We present a random sampling method for learning structured dynamical systems from under-sampled and possibly noisy state-space…

Information Theory · Computer Science 2018-05-14 Hayden Schaeffer , Giang Tran , Rachel Ward , Linan Zhang

Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform or heuristic non-uniform sparsity budgets which have…

Machine Learning · Computer Science 2020-06-24 Aditya Kusupati , Vivek Ramanujan , Raghav Somani , Mitchell Wortsman , Prateek Jain , Sham Kakade , Ali Farhadi

Feature selection is one of the most decisive tools in understanding data and machine learning models. Among other methods, sparsity induced by $L^{1}$ penalty is one of the simplest and best studied approaches to this problem. Although…

Machine Learning · Computer Science 2020-07-09 Andrii Trelin , Aleš Procházka

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where updating on new data erases previously acquired capabilities.…

Computation and Language · Computer Science 2025-10-20 Jessy Lin , Luke Zettlemoyer , Gargi Ghosh , Wen-Tau Yih , Aram Markosyan , Vincent-Pierre Berges , Barlas Oğuz

In this thesis we discuss machine learning methods performing automated variable selection for learning sparse predictive models. There are multiple reasons for promoting sparsity in the predictive models. By relying on a limited set of…

Machine Learning · Computer Science 2019-03-27 Magda Gregorova

With the dramatically increased number of parameters in language models, sparsity methods have received ever-increasing research focus to compress and accelerate the models. While most research focuses on how to accurately retain…

Artificial Intelligence · Computer Science 2022-05-24 Yuchao Li , Fuli Luo , Chuanqi Tan , Mengdi Wang , Songfang Huang , Shen Li , Junjie Bai

We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via ad hoc…

Computer Vision and Pattern Recognition · Computer Science 2018-05-23 Xiaojie Jin , Yingzhen Yang , Ning Xu , Jianchao Yang , Nebojsa Jojic , Jiashi Feng , Shuicheng Yan

Nowadays, the number of layers and of neurons in each layer of a deep network are typically set manually. While very deep and wide networks have proven effective in general, they come at a high memory and computation cost, thus making them…

Computer Vision and Pattern Recognition · Computer Science 2018-10-12 Jose M Alvarez , Mathieu Salzmann

An ensemble of neural networks is known to be more robust and accurate than an individual network, however usually with linearly-increased cost in both training and testing. In this work, we propose a two-stage method to learn Sparse…

Machine Learning · Statistics 2018-05-24 Yichi Zhang , Zhijian Ou

Employing equivariance in neural networks leads to greater parameter efficiency and improved generalization performance through the encoding of domain knowledge in the architecture; however, the majority of existing approaches require an a…

Machine Learning · Computer Science 2023-05-31 Emmanouil Theodosis , Karim Helwani , Demba Ba

We propose a practical method for $L_0$ norm regularization for neural networks: pruning the network during training by encouraging weights to become exactly zero. Such regularization is interesting since (1) it can greatly speed up…

Machine Learning · Statistics 2018-06-25 Christos Louizos , Max Welling , Diederik P. Kingma

Transformer-based Language Models have become ubiquitous in Natural Language Processing (NLP) due to their impressive performance on various tasks. However, expensive training as well as inference remains a significant impediment to their…

Machine Learning · Computer Science 2024-06-06 Amit Dhurandhar , Tejaswini Pedapati , Ronny Luss , Soham Dan , Aurelie Lozano , Payel Das , Georgios Kollias

Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically…

Sparsity in the structure of Neural Networks can lead to less energy consumption, less memory usage, faster computation times on convenient hardware, and automated machine learning. If sparsity gives rise to certain kinds of structure, it…

Machine Learning · Computer Science 2021-07-28 Julian Stier , Harshil Darji , Michael Granitzer