18 citations · 65 across the 18 of their papers we have counts for
21 papers
A Definition of Non-Stationary Bandits
Yueyang Liu, Xu Kuang, Benjamin Van Roy
Despite the subject of non-stationary bandit learning having attracted much recent attention, we have yet to identify a formal definition of non-stationarity that can consistently…
Experimenting under Stochastic Congestion
Shuangning Li, Ramesh Johari, Xu Kuang +1
We study randomized experiments in a service system when stochastic congestion can arise from temporarily limited supply or excess demand. Such congestion gives rise to cross-unit…
Non-Stationary Bandit Learning via Predictive Sampling
Yueyang Liu, Xu Kuang, Benjamin Van Roy
Thompson sampling has proven effective across a wide range of stationary bandit environments. However, as we demonstrate in this paper, it can perform poorly when applied to non-st…
Gaussian Imagination in Bandit Learning
Yueyang Liu, Adithya M. Devraj, Benjamin Van Roy +1
Assuming distributions are Gaussian often facilitates computations that are otherwise intractable. We study the performance of an agent that attains a bounded information ratio wit…
Learning and Information in Stochastic Networks and Queues
Neil Walton, Kuang Xu
We review the role of information and learning in the stability and optimization of queueing systems. In recent years, techniques from supervised learning, bandit learning and rein…
Hierarchical Causal Bandit
Ruiyang Song, Stefano Rini, Kuang Xu
Causal bandit is a nascent learning model where an agent sequentially experiments in a causal network of variables, in order to identify the reward-maximizing intervention. Despite…
A Bit Better? Quantifying Information for Bandit Learning
Adithya M. Devraj, Benjamin Van Roy, Kuang Xu
The information ratio offers an approach to assessing the efficacy with which an agent balances between exploration and exploitation. Originally, this was defined to be the ratio b…
Learner-Private Convex Optimization
Jiaming Xu, Kuang Xu, Dana Yang
Convex optimization with feedback is a framework where a learner relies on iterative queries and feedback to arrive at the minimizer of a convex function. It has gained considerabl…
Temporal Concatenation for Markov Decision Processes
Ruiyang Song, Kuang Xu
We propose and analyze a temporal concatenation heuristic for solving large-scale finite-horizon Markov decision processes (MDP), which divides the MDP into smaller sub-problems al…
Query Complexity of Bayesian Private Learning
Kuang Xu
We study the query complexity of Bayesian Private Learning: a learner wishes to locate a random target within an interval by submitting queries, in the presence of an adversary who…
Anonymous Stochastic Routing
Mine Su Erturk, Kuang Xu
We propose and analyze a recipient-anonymous stochastic routing model to study a fundamental trade-off between anonymity and routing delay. An agent wants to quickly reach a goal v…
Reinforcement with Fading Memories
Kuang Xu, Se-Young Yun
We study the effect of imperfect memory on decision making in the context of a stochastic sequential action-reward problem. An agent chooses a sequence of actions which generate di…
Information and Memory in Dynamic Resource Allocation
Kuang Xu, Yuan Zhong
We propose a general framework, dubbed Stochastic Processing under Imperfect Information (SPII), to study the impact of information constraints and memories on dynamic resource all…
Experimenting in Equilibrium
Stefan Wager, Kuang Xu
Classical approaches to experimental design assume that intervening on one unit does not affect other units. There are many important settings, however, where this non-interference…
Private Sequential Learning
John N. Tsitsiklis, Kuang Xu, Zhi Xu
We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine…
On the capacity of information processing systems
Laurent Massoulie, Kuang Xu
We propose and analyze a family of information processing systems, where a finite set of experts or servers are employed to extract information about a stream of incoming jobs. Eac…
Necessity of Future Information in Admission Control
Kuang Xu
We study the necessity of predictive information in a class of queueing admission control problems, where a system manager is allowed to divert incoming jobs up to a fixed rate, in…
Flexible Queueing Architectures
John N. Tsitsiklis, Kuang Xu
We study a multi-server model with flexible servers and queues, connected through a bipartite graph, where the level of flexibility is captured by the graph's average degre…
Queuing with future information
Joel Spencer, Madhu Sudan, Kuang Xu
We study an admissions control problem, where a queue with service rate receives incoming jobs at rate , and the decision maker is allowed to redirect away jobs…
On the Power of Centralization in Distributed Processing
Kuang Xu
In this thesis, we propose and analyze a multi-server model that captures a performance trade-off between centralized and distributed processing. In our model, a fraction of an…
Go Viral, or Not: Rate-Optimal Control for Resource-Constrained Branching Processes
Shie Mannor, Kuang Xu
We propose and analyze a new class of controlled multi-type branching processes with a per-step linear resource constraint, motivated by potential applications in viral marketing a…