Foundations.ai
Overview
Core theoretical underpinnings of AI, spanning probabilistic inference and learning theory, algorithmic complexity and guarantees, causal reasoning, and formal methods—all aimed at rigorously understanding when and why AI techniques work.
Location
KR 3
Principal Investigators
Recent Publications
-
Clustering under Constraints: Efficient Parameterized Approximation Schemes
Sujoy Bhore, A. Gadekar, T. Inamdar
Innovations in Theoretical Computer Science Conference (ITCS) · 2027
-
Geometric Hashing in MPC with Applications to Clustering and Stochastic Embeddings
Sujoy Bhore, Arnold Filtser, Eunjin Oh, Hyeonjun Shin, Himanshi Singh
ACM-SIAM Symposium on Discrete Algorithms (SODA) · 2027
-
An Efficient Joint Learning Approach for Item Response Theory
Tanish Agarwal, Kaustubh Sejole, Arpit Agarwal
International Conference on Machine Learning (ICML) · 2026
-
Expectation Maximization (EM) Converges for General Agnostic Mixtures
IEEE International Symposium on Information Theory (ISIT) · 2026
-
Finding the Signal in the Spam: Jointly Learning Rewards and Worker Reliability from Pairwise Comparisons
Kaustubh Shivshankar Shejole, Tanish Agarwal, Arpit Agarwal, Avishek Ghosh
Conference on Uncertainty in Artificial Intelligence (UAI) · 2026
-
Matching Markets meet Cumulative Prospect Theory: Towards Optimal and Adversarially Robust Learning
Ananya Kunisetty, Avishek Ghosh
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD) · 2026
-
Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret
Conference on Neural Information Processing Systems (NeurIPS) · 2026
-
Non-Clashing Teaching in Graphs: Algorithms, Complexity, and Bounds
Sujoy Bhore, Liana Khazaliya, Fionn Mc Inerney
International Conference on Learning Representations (ICLR) · 2026
-
On the Theory of Continual Learning with Gradient Descent for Neural Networks
Hossein Taheri, Avishek Ghosh, Arya Mazumdar
International Conference on Machine Learning (ICML) · 2026
-
Optimal Regret for Single Index Bandits
Devdan Dey, Sujoy Bhore, Avishek Ghosh
Preprint · 2026