3 citations · 7 across the 11 of their papers we have counts for
13 papers
Catoni-style Confidence Sequences under Infinite Variance
Sujay Bhatt, Guanhua Fang, Ping Li +1
In this paper, we provide an extension of confidence sequences for settings where the variance of the data-generating distribution does not exist or is infinite. Confidence sequenc…
Oracle-free Reinforcement Learning in Mean-Field Games along a Single Sample Path
Muhammad Aneeq uz Zaman, Alec Koppel, Sujay Bhatt +1
We consider online reinforcement learning in Mean-Field Games (MFGs). Unlike traditional approaches, we alleviate the need for a mean-field oracle by developing an algorithm that a…
Offline Change Detection under Contamination
Sujay Bhatt, Guanhua Fang, Ping Li
In this work, we propose a non-parametric and robust change detection algorithm to detect multiple change points in time series data under contamination. The contamination model is…
Adversarial Linear-Quadratic Mean-Field Games over Multigraphs
Muhammad Aneeq uz Zaman, Sujay Bhatt, Tamer Başar
In this paper, we propose a game between an exogenous adversary and a network of agents connected via a multigraph. The multigraph is composed of (1) a global graph structure, capt…
Extreme Bandits using Robust Statistics
Sujay Bhatt, Ping Li, Gennady Samorodnitsky
We consider a multi-armed bandit problem motivated by situations where only the extreme values, as opposed to expected values in the classical bandit setting, are of interest. We p…
Policy Gradient using Weak Derivatives for Reinforcement Learning
Sujay Bhatt, Alec Koppel, Vikram Krishnamurthy
This paper considers policy search in continuous state-action reinforcement learning problems. Typically, one computes search directions using a classic expression for the policy g…
Adaptive Polling in Hierarchical Social Networks using Blackwell Dominance
Sujay Bhatt, Vikram Krishnamurthy
Consider a population of individuals that observe an underlying state of nature that evolves over time. The population is classified into different levels depending on the hierarch…
Controlled Information Fusion with Risk-Averse CVaR Social Sensors
Sujay Bhatt, Vikram Krishnamurthy
Consider a multi-agent network comprised of risk averse social sensors and a controller that jointly seek to estimate an unknown state of nature, given noisy measurements. The netw…
Multiple Stopping Time POMDPs: Structural Results & Application in Interactive Advertising in Social Media
Vikram Krishnamurthy, Anup Aprem, Sujay Bhatt
This paper considers a multiple stopping time problem for a Markov chain observed in noise, where a decision maker chooses at most L stopping times to maximize a cumulative objecti…
Controlled Sequential Information Fusion with Social Sensors
Sujay Bhatt, Vikram Krishnamurthy
A sequence of social sensors estimate an unknown parameter (modeled as a state of nature) by performing Bayesian Social Learning, and myopically optimize individual reward function…
Opportunistic Advertisement Scheduling in Live Social Media: A Multiple Stopping Time POMDP Approach
Vikram Krishnamurthy, Anup Aprem, Sujay Bhatt
Live online social broadcasting services like YouTube Live and Twitch have steadily gained popularity due to improved bandwidth, ease of generating content and the ability to earn…
Tracking Infection Diffusion in Social Networks: Filtering Algorithms and Threshold Bounds
Vikram Krishnamurthy, Sujay Bhatt, Tavis Pedersen
This paper deals with the statistical signal pro- cessing over graphs for tracking infection diffusion in social networks. Infection (or Information) diffusion is modeled using the…
Sequential Detection of Market shocks using Risk-averse Agent Based Models
Vikram Krishnamurthy, Sujay Bhatt
This paper considers a statistical signal processing problem involving agent based models of financial markets which at a micro-level are driven by socially aware and risk- averse…