Publications

• ArXiv

• Google Scholar

• ResearchGate

Journal Articles

• P Mayekar^*, S Jha, A T Suresh, and H Tyagi. Wyner-Ziv Estimators for Distributed Mean Estimation with Side Information and Optimization, submitted.




• S Jha^*, P Mayekar , and H Tyagi. Fundamental limits of over-the-air optimization: Are analog schemes optimal?, IEEE Journal on Selected Areas in Information Theory (Special Issue on Distributed Coding and Computation).




• P Mayekar^* and H Tyagi. RATQ: A Universal Fixed-Length Quantizer for Stochastic Optimization, IEEE Transactions on Information Theory. paper.

  
  

• P Mayekar^*, P Parag, and H Tyagi. Optimal Source Codes for Timely Updates, IEEE Transactions on Information Theory. paper.

Conference Proceedings

• P Mayekar^*, J Scarlett, and V Tan. Communication-Constrained Bandits under Additive Gaussian Noise , in proceedings of International Conference on Machine Learning (ICML), 2023, Hawaii, USA.



• S Jha^* and P Mayekar . Fundamental Limits of Distributed Optimization over Multiple Access Channel, in proceedings of IEEE Information Theory Workshop (ITW), 2023, Saint-Malo, France. paper.




• P Mayekar^*, S Jha, and H Tyagi. Wyner-Ziv compression is (almost) optimal for distributed optimization in proceedings of IEEE International Symposium on Information Theory (ISIT), 2022, Aalto, Finland. paper.




• S Jha^*, P Mayekar, and H Tyagi. Fundamental limits of over-the-air optimization: Are analog schemes optimal? in proceedings of IEEE Global Communications Conference (GLOBECOM), 2021, Madrid, Spain. paper. talk (by Shubham).




• J Acharya, C Canonne, P Mayekar^*, and H Tyagi. Information-constrained optimization: Can adaptive processing of gradients help?, in proceedings of Neural Information Processing Systems (NeurIPS), 2021. paper. poster. slides. talk.




• P Mayekar^*, A T Suresh, and H Tyagi. Wyner-Ziv Estimators: Efficient Distributed Mean Estimation with Side Information in proceedings of International Conference on Artificial Intelligence and Statistics (AISTATS), 2021. paper. poster. slides. short talk.




• P Mayekar^* and H Tyagi. Limits on gradient compression for stochastic optimization in proceedings of IEEE International Symposium on Information Theory (ISIT), 2020, Los Angeles, USA. paper. slides. talk.




• P Mayekar^* and H Tyagi. RATQ: A Universal Fixed-Length Quantizer for Stochastic Optimization in proceedings of International Conference on Artificial Intelligence and Statistics (AISTATS), 2020, Palermo, Italy. paper. slides. talk.

  
  

• P Mayekar^*, P Parag, and H Tyagi. Optimal Lossless Source Codes for Timely Updates in proceedings of IEEE International Symposium on Information Theory (ISIT), 2018, Vail, USA. paper. slides. talk (by Himanshu). (Jack Keil Wolf Student Paper Award at ISIT 2018)