7.7k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Harish-Chandra Research InstituteIN27 papers
- International Institute of Information TechnologyIN23 papers
- Homi Bhabha National InstituteIN20 papers
- Indian Institute of Science Education and Research ThiruvananthapuramIN20 papers
- Indian Institute of Science BangaloreIN15 papers
- Indian Institute of Technology HyderabadIN14 papers
- Institute of Physics, BhubaneshwarIN11 papers
- Birla Institute of Technology and Science, PilaniIN10 papers
- National University of SingaporeSG9 papers
- Indian Institute of Technology KanpurIN8 papers
- Université Libre de BruxellesBE8 papers
- Birla Institute of Technology and Science - Hyderabad CampusIN7 papers
6 papers · 2 filters
Reducing the Variance of Variational Estimates of Mutual Information by Limiting the Critic's Hypothesis Space to RKHS
P Aditya Sreekar, Ujjwal Tiwari, Anoop Namboodiri
Mutual information (MI) is an information-theoretic measure of dependency between two random variables. Several methods to estimate MI, from samples of two random variables with un…
Maximum Reward Formulation In Reinforcement Learning
Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall +6
Reinforcement learning (RL) algorithms typically deal with maximizing the expected cumulative return (discounted or undiscounted, finite or infinite horizon). However, several cruc…
Off-policy Bandits with Deficient Support
Noveen Sachdeva, Yi Su, Thorsten Joachims
Learning effective contextual-bandit policies from past actions of a deployed system is highly desirable in many settings (e.g. voice assistants, recommendation, search), since it…
Learning Multiclass Classifier Under Noisy Bandit Feedback
Mudit Agarwal, Naresh Manwani
This paper addresses the problem of multiclass classification with corrupted or noisy bandit feedback. In this setting, the learner may not receive true feedback. Instead, it recei…
Robust Deep Ordinal Regression Under Label Noise
Bhanu Garg, Naresh Manwani
The real-world data is often susceptible to label noise, which might constrict the effectiveness of the existing state of the art algorithms for ordinal regression. Existing works…
Ballooning Multi-Armed Bandits
Ganesh Ghalme, Swapnil Dhamal, Shweta Jain +2
In this paper, we introduce Ballooning Multi-Armed Bandits (BL-MAB), a novel extension of the classical stochastic MAB model. In the BL-MAB model, the set of available arms grows (…