no code implementations • 22 May 2024 • Sagnik Chatterjee, Manuj Mukherjee, Alhad Sethi
We show that the generalization error of statistical learners in the dependent data setting is equivalent to the generalization error of statistical learners in the i. i. d.
no code implementations • 6 Jul 2023 • Sagnik Chatterjee, Vyacheslav Kungurtsev
In this work, we propose a novel architecture (and several variants thereof) based on quantum cryptographic primitives with provable privacy and security guarantees regarding membership inference attacks on generative models.
no code implementations • 1 Oct 2022 • Sagnik Chatterjee, Tharrmashastha SAPV, Debajyoti Bera
Our algorithm is the first algorithm (classical or quantum) for learning decision trees in polynomial time without membership queries.
1 code implementation • 25 Oct 2021 • Debajyoti Bera, Rohan Bhatia, Parmeet Singh Chani, Sagnik Chatterjee
Izdebski et al. posed an open question on whether we can boost quantum weak learners that output non-binary hypothesis.