37 citations · 87 across the 19 of their papers we have counts for
23 papers
Probabilistic Hash Embeddings for Online Learning of Categorical Features
Aodong Li, Abishek Sankararaman, Balakrishnan Narayanaswamy
We study streaming data with categorical features where the vocabulary of categorical feature values is changing and can even grow unboundedly over time. Feature hashing is commonl…
ODIN: A NL2SQL Recommender to Handle Schema Ambiguity
Kapil Vaidya, Abishek Sankararaman, Jialin Ding +4
NL2SQL (natural language to SQL) systems translate natural language into SQL queries, allowing users with no technical background to interact with databases and create tools like r…
Competing Bandits in Decentralized Contextual Matching Markets
Satush Parikh, Soumya Basu, Avishek Ghosh +1
Sequential learning in a multi-agent resource constrained matching market has received significant interest in the past few years. We study decentralized learning in two-sided matc…
Online Heavy-tailed Change-point detection
Abishek Sankararaman, Balakrishnan, Narayanaswamy
We study algorithms for online change-point detection (OCPD), where samples that are potentially heavy-tailed, are presented one at a time and a change in the underlying mean must…
Predict-and-Critic: Accelerated End-to-End Predictive Control for Cloud Computing through Reinforcement Learning
Kaustubh Sridhar, Vikramank Singh, Balakrishnan Narayanaswamy +1
Cloud computing holds the promise of reduced costs through economies of scale. To realize this promise, cloud computing vendors typically solve sequential resource allocation probl…
Double Auctions with Two-sided Bandit Feedback
Soumya Basu, Abishek Sankararaman
Double Auction enables decentralized transfer of goods between multiple buyers and sellers, thus underpinning functioning of many online marketplaces. Buyers and sellers compete in…
Decentralized Competing Bandits in Non-Stationary Matching Markets
Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran +2
Understanding complex dynamics of two-sided online matching markets, where the demand-side agents compete to match with the supply-side (arms), has recently received substantial in…
Breaking the Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits
Avishek Ghosh, Abishek Sankararaman
We prove an instance independent (poly) logarithmic regret for stochastic contextual bandits with linear payoff. Previously, in \cite{chu2011contextual}, a lower bound of $\mathcal…
Model Selection for Generic Contextual Bandits
Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran
We consider the problem of model selection for the general stochastic contextual bandits under the realizability assumption. We propose a successive refinement based algorithm call…
Adaptive Clustering and Personalization in Multi-Agent Stochastic Linear Bandits
Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran
We consider the problem of minimizing regret in an agent heterogeneous stochastic linear bandits framework, where the agents (users) are similar but not all identical. We model…
Beyond Regret for Decentralized Bandits in Matching Markets
Soumya Basu, Karthik Abinav Sankararaman, Abishek Sankararaman
We design decentralized algorithms for regret minimization in the two-sided matching market with one-sided bandit feedback that significantly improves upon the prior works (Liu et…
Multi-Agent Low-Dimensional Linear Bandits
Ronshee Chawla, Abishek Sankararaman, Sanjay Shakkottai
We study a multi-agent stochastic linear bandit with side information, parameterized by an unknown vector . The side information consists of a finite collecti…
Problem-Complexity Adaptive Model Selection for Stochastic Linear Bandits
Avishek Ghosh, Abishek Sankararaman, Kannan Ramchandran
We consider the problem of model selection for two popular stochastic linear bandit settings, and propose algorithms that adapts to the unknown problem complexity. In the first set…
Dominate or Delete: Decentralized Competing Bandits in Serial Dictatorship
Abishek Sankararaman, Soumya Basu, Karthik Abinav Sankararaman
Online learning in a two-sided matching market, with demand side agents continuously competing to be matched with supply side (arms), abstracts the complex interactions under parti…
Ergodicity and steady state analysis for Interference Queueing Networks
Sayan Banerjee, Abishek Sankararaman
We analyze an interacting queueing network on that was introduced in Sankararaman-Baccelli-Foss (2019) as a model for wireless networks. We show that the marginals o…
Stability and Scalability of Blockchain Systems
Aditya Gopalan, Abishek Sankararaman, Anwar Walid +1
The blockchain paradigm provides a mechanism for content dissemination and distributed consensus on Peer-to-Peer (P2P) networks. While this paradigm has been widely adopted in indu…
The Gossiping Insert-Eliminate Algorithm for Multi-Agent Bandits
Ronshee Chawla, Abishek Sankararaman, Ayalvadi Ganesh +1
We consider a decentralized multi-agent Multi Armed Bandit (MAB) setup consisting of agents, solving the same MAB instance to minimize individual cumulative regret. In our mode…
ComHapDet: A Spatial Community Detection Algorithm for Haplotype Assembly
Abishek Sankararaman, Haris Vikalo, François Baccelli
Background: Haplotypes, the ordered lists of single nucleotide variations that distinguish chromosomal sequences from their homologous pairs, may reveal an individual's susceptibil…
Social Learning in Multi Agent Multi Armed Bandits
Abishek Sankararaman, Ayalvadi Ganesh, Sanjay Shakkottai
In this paper, we introduce a distributed version of the classical stochastic Multi-Arm Bandit (MAB) problem. Our setting consists of a large number of agents that collaborativ…
Interference Queueing Networks on Grids
Abishek Sankararaman, François Baccelli, Sergey Foss
Consider a countably infinite collection of interacting queues, with a queue located at each point of the -dimensional integer grid, having independent Poisson arrivals, but dep…
Community Detection on Euclidean Random Graphs
Emmanuel Abbe, Francois Baccelli, Abishek Sankararaman
We study the problem of community detection (CD) on Euclidean random geometric graphs where each vertex has two latent variables: a binary community label and a valu…
Spatial Birth-Death Wireless Networks
Abishek Sankararaman, Francois Baccelli
We propose and study a novel continuous space-time model for wireless networks which takes into account the stochastic interactions in both space through interference and in time d…
Performance-Oriented Association in Large Cellular Networks with Technology Diversity
Abishek Sankararaman, Jeong-woo Cho, Francois Baccelli
The development of mobile virtual network operators, where multiple wireless technologies (e.g. 3G and 4G) or operators with non-overlapping bandwidths are pooled and shared is exp…