Sparsity is essential for deploying large models on resource constrained edge platforms. However, optimizing sparsity patterns for individual tasks in isolation ignores the significant I/O overhead incurred during frequent task switching. We introduce an on-demand multi-task sparsity framework specifically designed to minimize switching costs by maximizing parameter reuse. Unlike monolithic approaches, we decompose weights into reusable block-granular units and align sparse structures across tasks to maximize overlap. By dynamically loading only the small differential set of blocks required for the next task, our method effectively mitigates the cold-start latency inherent in traditional monolithic approaches.Experiments on a real-world autonomous driving platform demonstrate that our framework achieves superior switching efficiency, accelerating task switching by over 6.6X on average compared to existing sparsity methods.
Dynamic Pricing and Demand Learning on a Large Network of Products: A PAC-Bayesian Approach
Duke University, Fuqua School of Business(杜克大学富卡商学院);Institute for Data, Systems, and Society, MIT(麻省理工学院数据、系统与社会研究所);Operations Research Center, MIT(麻省理工学院运筹学中心)
On-Demand Model and Client Deployment in Federated Learning with Deep Reinforcement Learning
Concordia University(康考迪亚大学);Mohammad Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学);Lebanese American University(黎巴嫩美国大学);Khalifa University(哈利法大学)
ON-DEMAND-FL: A Dynamic and Efficient Multi-Criteria Federated Learning Client Deployment Scheme
Lebanese American University(黎巴嫩美国大学);Concordia University(康考迪亚大学);New York University(纽约大学);Zayed University(扎耶德大学);Khalifa University(哈利法大学);Mohammad Bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
Feature Selection and Regularization in Multi-Class Classification: An Empirical Study of One-vs-Rest Logistic Regression with Gradient Descent Optimization and L1 Sparsity Constraints
Department of Computer Science and Software Engineering, Auburn University, Alabama, USA(计算机科学与软件工程系,阿伯茨费尔德大学,美国阿拉巴马州);Department of Information and Communication Technology, Bangladesh University of Professionals, Dhaka, Bangladesh(信息与通信技术系,孟加拉国专业大学,达卡)
Computing Systems Laboratory (CSLab), National Technical University of Athens, Greece(计算系统实验室(CSLab),国家技术大学(雅典));Artificial Intelligence and Learning Systems Laboratory (AILS), National Technical University of Athens, Greece(人工智能与学习系统实验室(AILS),国家技术大学(雅典));Intelligent Robotics and Automation Laboratory (IRAL), National Technical University of Athens, Greece(智能机器人与自动化实验室(IRAL),国家技术大学(雅典));Max Planck Institute for Software Systems (MPI-SWS), Germany(马克斯·普朗克软件系统研究所(MPI-SWS),德国);School of Computing Science, University of Glasgow, United Kingdom(计算科学学院,格拉斯哥大学)
Accelerating Linear Recurrent Neural Networks for the Edge with Unstructured Sparsity
Neuromorphic Computing Lab, Intel Corporation, USA;Institute of Informatics, LMU Munich, Germany;Bernoulli Institute \& CogniGron, University of Groningen, Netherlands