Prof. Arindam Banerjee
Founder Professor in Engineering
University of Illinois Urbana-Champaign
Arindam Banerjee is a Founder Professor at the School of Computing and Data Science, University of Illinois Urbana-Champaign. He currently serves as the President of the Society for Artificial Intelligence and Statistics which runs the annual AISTATS conferences and is an ACM Fellow. His research interests are in machine learning and artificial intelligence. His current research focuses on computational and statistical aspects of over-parameterized models including deep learning, spatial and temporal data analysis, generative models, and sequential decision making problems. His work also focuses on applications of machine learning in complex real-world and scientific domains including problems in climate science, ecology, and finance. He has won several awards over the years, including seven best paper awards at top-tier venues.
Research Interests
- Machine Learning
- Artificial Intelligence
- Data Mining
Research Focus
Computational and statistical aspects of over-parameterized models including deep learning and generative models
Selected Publications
- Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
Rohan Deb, Qiaobo Li, Mayank Shrivastava, Arindam Banerjee
International Conference on Artificial Intelligence and Statistics (AISTATS) (Spotlight) 2026 (arXiv). - Model Predictive Control with Differentiable World Models for Offline Reinforcement Learning
Rohan Deb, Stephen J. Wright, Arindam Banerjee
ICLR Workshop on World Models, 2026 (arXiv). - Gradual Fine-Tuning for Flow Matching Models
Gudrun Thorkelsdottir, Arindam Banerjee
ICLR Workshop on Deep Generative Models, 2026 (arXiv). - TorchGeo 1.0: Satellite Image Time Series, and Beyond!
Stewart, Adam J.; Falkena, Sieger; Corley, Isaac A.; Kristen, Harald; Eves, Keenan; Chang, Yi-Chia; Nagda, Chandni; Schindlegger, Frederick; Mu, Yang; Lehmann, Nils; Banerjee, Arindam; Zhu, Xiao Xiang
International Society for Photogrammetry and Remote Sensing (ISPRS) Congress, 2026. - Sketched Gaussian Mechanism for Private Federated Learning
Qiaobo Li, Zhijie Chen, and Arindam Banerjee
Advances in Neural Information Processing Systems (NeurIPS) (Spotlight), 2025, (arXiv). - Sketched Adaptive Federated Deep Learning: A Sharp Convergence Analysis
Zhijie Chen, Qiaobo Li, and Arindam Banerjee
Advances in Neural Information Processing Systems (NeurIPS), 2025, (arXiv). - Optimization for Neural Operators can Benefit from Width
Pedro Cisneros-Velarde, Bhavesh Shrimali, and Arindam Banerjee
International Conference on Machine Learning (ICML), 2025 (arXiv). - On the Generalizability of Foundation Models for Crop Type Mapping
Y.-C. Chang, A. J. Stewart, F. Bastani, P. Wolters, S. Kannan, G. R. Huber, J. Wang, and A. Banerjee
IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2025 (arxiv). - Conservative Contextual Bandits: Beyond Linear Representations
Rohan Deb, Mohammad Ghavamzadeh, and Arindam Banerjee
International Conference on Learning Representations (ICLR), 2025.(arXiv) - Loss Gradient Gaussian Width based Generalization and Optimization Guarantees
A. Banerjee, Q. Li, and Y. Zhou
International Conference on Artificial Intelligence and Statistics (AISTATS) (Oral) 2025. (arxiv) - Optimization and Generalization Guarantees for Weight Normalization
P. Cisneros-Velarde, Z. Chen, S. Koyejo, and A. Banerjee
Transactions of Machine Learning Research (TMLR), 2025. (arxiv) - Computationally Efficient Methods for Invariant Feature Selection with Sparsity
Jane Du and Arindam Banerjee
Conference on Uncertainty in Artificial Intelligence (UAI) , 2025. - Multi-Stage Probabilistic Generative Super Resolution with Scarce High-Resolution Data
R. Zhu, M. Weston, H. Zhang, and A. Banerjee
Conference on Uncertainty in Artificial Intelligence (UAI) , 2025.
