Posts by Collection

portfolio

publications

Improvable Gap Balancing for Multi-Task Learning

Published in 39th Conference on Uncertainty in Artificial Intelligence (UAI 2023), 2023

We propose two novel improvable gap balancing algorithms for multi-task learning, instead of the classic loss balancing strategy: one takes a simple heuristic, and the other (for the first time) deploys deep reinforcement learning for MTL.

Download here

talks

teaching

Teaching experience 1

Undergraduate course, University 1, Department, 2014

This is a description of a teaching experience. You can use markdown like any other post.

Teaching experience 2

Workshop, University 1, Department, 2015

This is a description of a teaching experience. You can use markdown like any other post.