no code implementations • 10 Feb 2024 • Han Shen, Zhuoran Yang, Tianyi Chen
But bilevel problems such as incentive design, inverse reinforcement learning (RL), and RL from human feedback (RLHF) are often modeled as dynamic objective functions that go beyond the simple static objective structures, which pose significant challenges of using existing bilevel solutions.
1 code implementation • 13 Jan 2024 • A F M Saif, Xiaodong Cui, Han Shen, Songtao Lu, Brian Kingsbury, Tianyi Chen
In this paper, we present a novel bilevel optimization-based training approach to training acoustic models for automatic speech recognition (ASR) tasks that we term {bi-level joint unsupervised and supervised training (BL-JUST)}.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • 10 Feb 2023 • Han Shen, Quan Xiao, Tianyi Chen
Bilevel optimization enjoys a wide range of applications in hyper-parameter optimization, meta-learning and reinforcement learning.
1 code implementation • 14 Nov 2022 • Quan Xiao, Han Shen, Wotao Yin, Tianyi Chen
By leveraging the special structure of the equality constraints problem, the paper first presents an alternating implicit projected SGD approach and establishes the $\tilde{\cal O}(\epsilon^{-2})$ sample complexity that matches the state-of-the-art complexity of ALSET \citep{chen2021closing} for unconstrained bilevel problems.
1 code implementation • 23 Oct 2022 • Heshan Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen
Machine learning problems with multiple objective functions appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimized jointly, sharing inductive bias between them.
no code implementations • 21 Jun 2022 • Han Shen, Tianyi Chen
Stochastic approximation (SA) with multiple coupled sequences has found broad applications in machine learning such as bilevel learning and reinforcement learning (RL).
no code implementations • 31 Dec 2020 • Han Shen, Kaiqing Zhang, Mingyi Hong, Tianyi Chen
Asynchronous and parallel implementation of standard reinforcement learning (RL) algorithms is a key enabler of the tremendous success of modern RL.
no code implementations • 4 Mar 2020 • Tao Hu, Lichao Huang, Han Shen
Recent works in multiple object tracking use sequence model to calculate the similarity score between the detections and the previous tracklets.
no code implementations • 20 Feb 2020 • Tao Sun, Han Shen, Tianyi Chen, Dongsheng Li
Typically, the performance of TD(0) and TD($\lambda$) is very sensitive to the choice of stepsizes.
no code implementations • 13 Dec 2019 • Haojie Liu, Han Shen, Lichao Huang, Ming Lu, Tong Chen, Zhan Ma
Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency.
1 code implementation • 2 Aug 2019 • Tao Hu, Lichao Huang, Xian-Ming Liu, Han Shen
Our tracker achieves leading performance in OTB2013, OTB2015, VOT2015, VOT2016 and LaSOT, and operates at a real-time speed of 26 FPS, which indicates our method is effective and practical.
no code implementations • 11 Jul 2019 • Hao Luo, Lichao Huang, Han Shen, Yuan Li, Chang Huang, Xinggang Wang
Without any bells and whistles, our method obtains 80. 3\% mAP on the ImageNet VID dataset, which is superior over the previous state-of-the-arts.
1 code implementation • 2 Jul 2019 • Qiang Zhou, Zilong Huang, Lichao Huang, Yongchao Gong, Han Shen, Chang Huang, Wenyu Liu, Xinggang Wang
Video object segmentation (VOS) aims at pixel-level object tracking given only the annotations in the first frame.
Ranked #1 on Visual Object Tracking on YouTube-VOS 2018 (Jaccard (Seen) metric)
no code implementations • 5 Aug 2018 • Han Shen, Lichao Huang, Chang Huang, Wei Xu
The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted cost function of data association stage, which prevents the tracking goals from learning directly from the feature.