English
Related papers

Related papers: Learning Sparse Sharing Architectures for Multiple…

200 papers

Previous work has suggested that parameter sharing between transition-based neural dependency parsers for related languages can lead to better performance, but there is no consensus on what parameters to share. We present an evaluation of…

Computation and Language · Computer Science 2018-10-08 Miryam de Lhoneux , Johannes Bjerva , Isabelle Augenstein , Anders Søgaard

We investigate task clustering for deep-learning based multi-task and few-shot learning in a many-task setting. We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario.…

Machine Learning · Computer Science 2018-05-21 Mo Yu , Xiaoxiao Guo , Jinfeng Yi , Shiyu Chang , Saloni Potdar , Gerald Tesauro , Haoyu Wang , Bowen Zhou

Parameter sharing, where each agent independently learns a policy with fully shared parameters between all policies, is a popular baseline method for multi-agent deep reinforcement learning. Unfortunately, since all agents share the same…

Machine Learning · Computer Science 2023-11-01 J. K. Terry , Nathaniel Grammel , Sanghyun Son , Benjamin Black , Aakriti Agrawal

Parameter regularization or allocation methods are effective in overcoming catastrophic forgetting in lifelong learning. However, they solve all tasks in a sequence uniformly and ignore the differences in the learning difficulty of…

Machine Learning · Computer Science 2023-04-12 Wenjin Wang , Yunqing Hu , Qianglong Chen , Yin Zhang

Recent years have seen an increasing popularity of learning the sparse \emph{changes} in Markov Networks. Changes in the structure of Markov Networks reflect alternations of interactions between random variables under different regimes and…

Machine Learning · Statistics 2017-01-10 Song Liu , Kenji Fukumizu , Taiji Suzuki

Multi-Task Learning is a learning paradigm that uses correlated tasks to improve performance generalization. A common way to learn multiple tasks is through the hard parameter sharing approach, in which a single architecture is used to…

Machine Learning · Computer Science 2022-04-15 Angelica Tiemi Mizuno Nakamura , Denis Fernando Wolf , Valdir Grassi

In this paper, we present a learning method for sequence labeling tasks in which each example sequence has multiple label sequences. Our method learns multiple models, one model for each label sequence. Each model computes the joint…

Machine Learning · Computer Science 2016-05-10 Arvind Agarwal , Saurabh Kataria

Modern deep models have massive parameter sizes, leading to high inference-time memory usage that limits practical deployment. Parameter sharing, a form of structured compression, effectively reduces redundancy, but existing approaches…

Machine Learning · Computer Science 2025-11-11 Boyang Zhang , Daning Cheng , Yunquan Zhang

Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to…

Machine Learning · Statistics 2014-12-04 Anastasia Pentina , Viktoriia Sharmanska , Christoph H. Lampert

Multitask learning aims at solving a set of related tasks simultaneously, by exploiting the shared knowledge for improving the performance on individual tasks. Hence, an important aspect of multitask learning is to understand the…

Machine Learning · Computer Science 2019-10-22 Changjian Shui , Mahdieh Abbasi , Louis-Émile Robitaille , Boyu Wang , Christian Gagné

Recently, end-to-end learning frameworks are gaining prevalence in the field of robot control. These frameworks input states/images and directly predict the torques or the action parameters. However, these approaches are often critiqued due…

Robotics · Computer Science 2016-09-29 Lerrel Pinto , Abhinav Gupta

Adapting neural networks to new tasks typically requires task-specific fine-tuning, which is time-consuming and reliant on labeled data. We explore a generative alternative that produces task-specific parameters directly from task identity,…

Machine Learning · Computer Science 2025-06-24 Lijun Zhang , Xiao Liu , Hui Guan

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge

Data scarcity poses a serious threat to modern machine learning and artificial intelligence, as their practical success typically relies on the availability of big datasets. One effective strategy to mitigate the issue of insufficient data…

Machine Learning · Computer Science 2026-05-14 Chaozhi Zhang , Lin Liu , Xiaoqun Zhang

Machine learning has witnessed tremendous success in solving tasks depending on a single hyperparameter. When considering simultaneously a finite number of tasks, multi-task learning enables one to account for the similarities of the tasks…

Machine Learning · Computer Science 2018-10-12 Romain Brault , Alex Lambert , Zoltán Szabó , Maxime Sangnier , Florence d'Alché-Buc

Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…

Computer Vision and Pattern Recognition · Computer Science 2020-09-14 Chang-Hui Liang , Wan-Lei Zhao , Run-Qing Chen

Inferring predictive maps between multiple input and multiple output variables or tasks has innumerable applications in data science. Multi-task learning attempts to learn the maps to several output tasks simultaneously with information…

Machine Learning · Statistics 2017-10-06 Ming Yu , Addie M. Thompson , Karthikeyan Natesan Ramamurthy , Eunho Yang , Aurélie C. Lozano

In this paper, a sparsity-aware adaptive algorithm for distributed learning in diffusion networks is developed. The algorithm follows the set-theoretic estimation rationale. At each time instance and at each node of the network, a closed…

Information Theory · Computer Science 2015-06-03 Symeon Chouvardas , Konstantinos Slavakis , Yannis Kopsinis , Sergios Theodoridis

Sparse modeling is a powerful framework for data analysis and processing. Traditionally, encoding in this framework is done by solving an l_1-regularized linear regression problem, usually called Lasso. In this work we first combine the…

Information Theory · Computer Science 2010-03-02 Pablo Sprechmann , Ignacio Ramirez , Guillermo Sapiro , Yonina C. Eldar

This paper presents a novel method that allows a machine learning algorithm following the transformation-based learning paradigm \cite{brill95:tagging} to be applied to multiple classification tasks by training jointly and simultaneously on…

Computation and Language · Computer Science 2007-05-23 Radu Florian , Grace Ngai
‹ Prev 1 3 4 5 6 7 10 Next ›