Aleksandr Podkopaev

According to our database, Aleksandr Podkopaev authored at least 5 papers between 2020 and 2023.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2023

Sequential Predictive Two-Sample and Independence Testing.

Aleksandr Podkopaev, Aaditya Ramdas

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Sequential Kernelized Independence Testing.

Aleksandr Podkopaev, Patrick Blöbaum, Shiva Prasad Kasiviswanathan, Aaditya Ramdas

Proceedings of the International Conference on Machine Learning, 2023

2022

Tracking the risk of a deployed model and detecting harmful distribution shifts.

Aleksandr Podkopaev, Aaditya Ramdas

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Distribution-free uncertainty quantification for classification under label shift.

Aleksandr Podkopaev, Aaditya Ramdas

Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence, 2021

2020

Distribution-free binary classification: prediction sets, confidence intervals and calibration.

Chirag Gupta, Aleksandr Podkopaev, Aaditya Ramdas

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020