paper-with-me

홈 › Papers

AutoScale: Linear Scalarization Guided by Multi-Task Optimization Metrics

2025-08-19 · Yi Yang, Kei Ikemura, Qingwen Zhang, Xiaomeng Zhu, Ci Li, Nazre Batool, Sina Sharif Mansouri, John Folkesson arxiv

Recent multi-task learning studies suggest that linear scalarization, when using well-chosen fixed task weights, can achieve comparable to or even better performance than complex multi-task optimization (MTO) methods. It remains unclear why certain weights yield optimal performance and how to determine these weights without relying on exhaustive hyperparameter search. This paper establishes a direct connection between linear scalarization and MTO methods, revealing through extensive experiments that well-performing scalarization weights exhibit specific trends in key MTO metrics, such as high gradient magnitude similarity. Building on this insight, we introduce AutoScale, a simple yet effective two-phase framework that uses these MTO metrics to guide weight selection for linear scalarization, without expensive weight search. AutoScale consistently shows superior performance with high efficiency across diverse datasets including a new large-scale benchmark.

📄 PDF Abstract BibTeX arXiv:2508.13979

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-Task Learning

Similar Papers 제목 키워드 기반

Optimal Scalarizations for Sublinear Hypervolume Regret

2023-07-06 · Qiuyi Zhang

Scalarization is a general, parallizable technique that can be deployed in any multiobjective setting to reduce multiple objectives into one, yet some have dismissed this versatile approach because linear scalarizations …

Bayesian Optimization

Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective

2023-08-27 · NeurIPS 2023 11

Linear scalarization, i.e., combining all loss functions by a weighted sum, has been the default choice in the literature of multi-task learning (MTL) since its inception. In recent years, there is a surge of interest in…

Multi-Task Learning

Online Mirror Descent for Tchebycheff Scalarization in Multi-Objective Optimization

2024-10-29 · Meitong Liu, Xiaoyuan Zhang, Chulin Xie, Kate Donahue 외

The goal of multi-objective optimization (MOO) is to learn under multiple, potentially conflicting, objectives. One widely used technique to tackle MOO is through linear scalarization, where one fixed preference vector i…

FairnessFederated Learning

CMI: An Online Multi-objective Genetic Autoscaler for Scientific and Engineering Workflows in Cloud Infrastructures with Unreliable Virtual Machines

2018-11-02 · David A. Monge, Elina Pacini, Cristian Mateos, Enrique Alba 외

Cloud Computing is becoming the leading paradigm for executing scientific and engineering workflows. The large-scale nature of the experiments they model and their variable workloads make clouds the ideal execution envir…

Cloud Computing

Reconstructing Physics-Informed Machine Learning for Traffic Flow Modeling: a Multi-Gradient Descent and Pareto Learning Approach

2025-05-19 · Yuan-Zheng Lei, Yaobang Gong, Dianwei Chen, Yao Cheng 외

Physics-informed machine learning (PIML) is crucial in modern traffic flow modeling because it combines the benefits of both physics-based and data-driven approaches. In conventional PIML, physical information is typical…

Physics-informed machine learning