166 citations · 625 across the 30 of their papers we have counts for
7 papers · 1 filter
Symphony in the Latent Space: Provably Integrating High-dimensional Techniques with Non-linear Machine Learning Models
Qiong Wu, Jian Li, Zhenming Liu +2
This paper revisits building machine learning algorithms that involve interactions between entities, such as those between financial assets in an actively managed portfolio, or int…
Knowledge-Guided Exploration in Deep Reinforcement Learning
Sahisnu Mazumder, Bing Liu, Shuai Wang +4
This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of state-action permissibility (SAP). Tw…
Semi-quantum private comparison and its generalization to the key agreement, summation, and anonymous ranking
Chong-Qiang Ye, Jian Li, Xiu-Bo Chen +2
Semi-quantum protocols construct connections between quantum users and ``classical'' users who can only perform certain ``classical'' operations. In this paper, we present a new se…
Simple and Optimal Stochastic Gradient Methods for Nonsmooth Nonconvex Optimization
Zhize Li, Jian Li
We propose and analyze several stochastic gradient algorithms for finding stationary points or local minimum in nonconvex, possibly with nonsmooth regularizer, finite-sum and onlin…
Analyzing Sharpness along GD Trajectory: Progressive Sharpening and Edge of Stability
Zhouzi Li, Zixuan Wang, Jian Li
Recent findings (e.g., arXiv:2103.00065) demonstrate that modern neural networks trained by full-batch gradient descent typically enter a regime called Edge of Stability (EOS). In…
Scalable Mediated Semi-quantum Key Distribution
Chong-Qiang Ye, Jian Li, Xiu-Bo Chen +1
Mediated semi-quantum key distribution (M-SQKD) permits two limited "semi-quantum" or "classical" users to establish a secret key with the help of a third party (TP), in which TP h…
Whittle Index based Q-Learning for Wireless Edge Caching with Linear Function Approximation
Guojun Xiong, Shufan Wang, Jian Li +1
We consider the problem of content caching at the wireless edge to serve a set of end users via unreliable wireless channels so as to minimize the average latency experienced by en…