Suprovat Ghoshal

Management Science and Operations Research · 2022

A researcher in the Science corpus: 1 paper; trusts 5 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Management Science and Operations Research — 9 citations into it
• Artificial Intelligence — 8 citations into it
• Reinforcement Learning — 8 citations into it

Whom Suprovat Ghoshal trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Aadirupa Saha
2. Aditya Gopalan
3. Radford M. Neal
4. Masrour Zoghi
5. Florian Heiss
6. Zohar S. Karnin
7. Yisong Yue
8. Thorsten Joachims
9. Róbert Istvan Busa-Fekete
10. Eyal Even-Dar

Who trusts Suprovat Ghoshal overall

1. Aldo Pacchiano
2. Banghua Zhu

Papers from Suprovat Ghoshal's perspective

Ordered by how strongly the researchers Suprovat Ghoshal trusts endorse each paper. Same corpus, a different order for every researcher.

1. Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems
2. Interactively optimizing information retrieval systems as a dueling bandits problem
3. PAC Subset Selection in Stochastic Multi-armed Bandits (International Conference on Machine Learning)
4. Pattern Recognition and Machine Learning
5. Reducing Dueling Bandits to Cardinal Bandits
6. Best Arm Identification in Multi-Armed Bandits
7. Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem
8. MergeRUCB: A Method for Large-Scale Online Ranker Evaluation
9. A Relative Exponential Weighing Algorithm for Adversarial Utility-based Dueling Bandits
10. Almost Optimal Exploration in Multi-Armed Bandits

Their papers

• Exploiting Correlation to Achieve Faster Learning Rates in Low-Rank Preference Bandits (2022) — 13 citations