Search Results for author: Han Shen

Found 14 papers, 6 papers with code

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF

no code implementations10 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.

Bilevel Optimization reinforcement-learning +1

Joint Unsupervised and Supervised Training for Automatic Speech Recognition via Bilevel Optimization

1 code implementation13 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

On Penalty-based Bilevel Gradient Descent Method

1 code implementation10 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.

Bilevel Optimization Meta-Learning +2

Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization

1 code implementation14 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.

Bilevel Optimization

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach

1 code implementation23 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.

Fairness Inductive Bias +1

A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences

no code implementations21 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).

Reinforcement Learning (RL)

Towards Understanding Asynchronous Advantage Actor-critic: Convergence and Linear Speedup

no code implementations31 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.

Atari Games OpenAI Gym +1

Multi-object Tracking via End-to-end Tracklet Searching and Ranking

no code implementations4 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.

Multi-Object Tracking Multiple Object Tracking

Adaptive Temporal Difference Learning with Linear Function Approximation

no code implementations20 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.

OpenAI Gym reinforcement-learning +1

Learned Video Compression via Joint Spatial-Temporal Correlation Exploration

no code implementations13 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.

Optical Flow Estimation Video Compression

Real Time Visual Tracking using Spatial-Aware Temporal Aggregation Network

1 code implementation2 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.

Motion Estimation Real-Time Visual Tracking

Object Detection in Video with Spatial-temporal Context Aggregation

no code implementations11 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.

Object object-detection +1

Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking

no code implementations5 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.

Multi-Object Tracking Multiple Object Tracking +1

Cannot find the paper you are looking for? You can Submit a new open access paper.