35 citations · 76 across the 18 of their papers we have counts for
20 papers
Generalization Properties of Retrieval-based Models
Soumya Basu, Ankit Singh Rawat, Manzil Zaheer
Many modern high-performing machine learning models such as GPT-3 primarily rely on scaling up models, e.g., transformer networks. Simultaneously, a parallel line of work aims to i…
No Regrets for Learning the Prior in Bandits
Soumya Basu, Branislav Kveton, Manzil Zaheer +1
We propose , a Thompson sampling algorithm that adapts sequentially to bandit tasks that it interacts with. The key idea in is to adapt to an unknown tas…
Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodes
Nihal Sharma, Rajat Sen, Soumya Basu +2
We study a variant of the contextual bandit problem where an agent can intervene through a set of stochastic expert policies. Given a fixed context, each expert samples actions fro…
Combinatorial Blocking Bandits with Stochastic Delays
Alexia Atsidakou, Orestis Papadigenopoulos, Soumya Basu +2
Recent work has considered natural variations of the multi-armed bandit problem, where the reward distribution of each arm is a special function of the time passed since its last p…
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…
Recoverability Landscape of Tree Structured Markov Random Fields under Symmetric Noise
Ashish Katiyar, Soumya Basu, Vatsal Shah +1
We study the problem of learning tree-structured Markov random fields (MRF) on discrete random variables with common support when the observations are corrupted by a -ary symmet…
On Generalization of Adaptive Methods for Over-parameterized Linear Regression
Vatsal Shah, Soumya Basu, Anastasios Kyrillidis +1
Over-parameterization and adaptive methods have played a crucial role in the success of deep learning in the last decade. The widespread use of over-parameterization has forced us…
Stochastic Linear Bandits with Protected Subspace
Advait Parulekar, Soumya Basu, Aditya Gopalan +2
We study a variant of the stochastic linear bandit problem wherein we optimize a linear objective function but rewards are accrued only orthogonal to an unknown subspace (which we…
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…
Contextual Blocking Bandits
Soumya Basu, Orestis Papadigenopoulos, Constantine Caramanis +1
We study a novel variant of the multi-armed bandit problem, where at each time step, the player observes an independently sampled context that determines the arms' mean rewards. Ho…
Bandits with Mean Bounds
Nihal Sharma, Soumya Basu, Karthikeyan Shanmugam +1
We study a variant of the bandit problem where side information in the form of bounds on the mean of each arm is provided. We prove that these translate to tighter estimates of sub…
Blocking Bandits
Soumya Basu, Rajat Sen, Sujay Sanghavi +1
We consider a novel stochastic multi-armed bandit setting, where playing an arm makes it unavailable for a fixed number of time slots thereafter. This models situations where reusi…
Learning Mixtures of Graphs from Epidemic Cascades
Jessica Hoffmann, Soumya Basu, Surbhi Goel +1
We consider the problem of learning the weighted edges of a balanced mixture of two undirected graphs from epidemic cascades. While mixture models are popular modeling tools, algor…
sAVSS: Scalable Asynchronous Verifiable Secret Sharing in BFT Protocols
Soumya Basu, Alin Tomescu, Ittai Abraham +3
This paper introduces a new way to incorporate verifiable secret sharing (VSS) schemes into Byzantine Fault Tolerance (BFT) protocols. This technique extends the threshold guarante…
Decentralization in Bitcoin and Ethereum Networks
Adem Efe Gencer, Soumya Basu, Ittay Eyal +2
Blockchain-based cryptocurrencies have demonstrated how to securely implement traditionally centralized systems, such as currencies, in a decentralized fashion. However, there have…
A Submodular Approach for Electricity Distribution Network Reconfiguration
Ali Khodabakhsh, Ger Yang, Soumya Basu +4
Distribution network reconfiguration (DNR) is a tool used by operators to balance line load flows and mitigate losses. As distributed generation and flexible load adoption increase…
Reconciling Selfish Routing with Social Good
Soumya Basu, Ger Yang, Thanasis Lianeas +2
Selfish routing is a central problem in algorithmic game theory, with one of the principal applications being that of routing in road networks. Inspired by the emergence of routing…
Adaptive TTL-Based Caching for Content Delivery
Soumya Basu, Aditya Sundarrajan, Javad Ghaderi +2
Content Delivery Networks (CDNs) deliver a majority of the user-requested content on the Internet, including web pages, videos, and software downloads. A CDN server caches and serv…
Effective Evaluation using Logged Bandit Feedback from Multiple Loggers
Aman Agarwal, Soumya Basu, Tobias Schnabel +1
Accurately evaluating new policies (e.g. ad-placement models, ranking functions, recommendation functions) is one of the key prerequisites for improving interactive systems. While…
New Complexity Results and Algorithms for the Minimum Tollbooth Problem
Soumya Basu, Thanasis Lianeas, Evdokia Nikolova
The inefficiency of the Wardrop equilibrium of nonatomic routing games can be eliminated by placing tolls on the edges of a network so that the socially optimal flow is induced as…