research

Working papers

• Geometrizing the cost of adaptation under differential privacy (working title) — T. Tony Cai, Abhinav Chakraborty, and Lasse Vuursteen

• A debiased semiparametric Bernstein–von Mises theorem for linear regression — Ismaël Castillo, Stéphanie van der Pas, Kolyan Ray, Aad van der Vaart, and Lasse Vuursteen

Under review

• The Cost of Adaptation under Differential Privacy: Optimal Adaptive Federated Density Estimation — T. Tony Cai, Abhinav Chakraborty, and Lasse Vuursteen

• Federated Nonparametric Hypothesis Testing with Differential Privacy Constraints: Optimal Rates and Adaptive Tests — T. Tony Cai, Abhinav Chakraborty, and Lasse Vuursteen

Published

• Optimal Federated Learning for Nonparametric Regression with Heterogeneous Distributed Differential Privacy Constraints — T. Tony Cai, Abhinav Chakraborty, and Lasse Vuursteen. JASA. arXiv

• Optimal federated learning for functional mean estimation under heterogeneous privacy constraints — T. Tony Cai, Abhinav Chakraborty, and Lasse Vuursteen. JRSSB. arXiv

• Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime — Lasse Vuursteen. NeurIPS.

• Optimal testing using combined test statistics across independent studies — Botond Szabó, Aad van der Vaart, Lasse Vuursteen, and Harry van Zanten. NeurIPS.

• Optimal high-dimensional and nonparametric distributed testing under communication constraints — Botond Szabó, Lasse Vuursteen, and Harry van Zanten. AoS.

• Optimal Distributed Composite Testing in High-dimensional Gaussian Models with 1-bit Communication — Botond Szabó, Lasse Vuursteen, and Harry van Zanten. IEEE Trans. Inf. Theory.