1 code implementation • 23 Feb 2024 • Hao Ban, Kaiyi Ji
Inspired by fair resource allocation in communication networks, we formulate the optimization of MTL as a utility maximization problem, where the loss decreases across tasks are maximized under different fairness measurements.
1 code implementation • NeurIPS 2023 • Peiyao Xiao, Hao Ban, Kaiyi Ji
In this paper, we propose a new direction-oriented multi-objective problem by regularizing the common descent direction within a neighborhood of a direction that optimizes a linear combination of objectives such as the average loss in MTL.
no code implementations • 12 Mar 2021 • Hao Ban, Pengtao Xie
Inspired by the interleaving learning technique of humans, in this paper we explore whether this learning methodology is beneficial for improving the performance of machine learning models as well.
no code implementations • 9 Dec 2020 • Pengtao Xie, Xuefeng Du, Hao Ban
To achieve this goal, we develop a general framework -- Skillearn, which provides a principled way to represent humans' learning skills mathematically and use the formally-represented skills to improve the training of ML models.