The Gaussian Mixing Mechanism: Renyi Differential Privacy via Gaussian Sketches
(opens in new window)
Author(s):
Omri Lev, Vishwak Srinivasan, Moshe Shenfeld, Katrina Ligett, Ayush Sekhari, Ashia Wilson
Published in:
Advances in Neural Information Processing Systems 38, 2025
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI:
10.52202/085713-1690
Fair Decisions from Calibrated Scores: Achieving Optimal Classification While Satisfying Sufficiency
(opens in new window)
Author(s):
Etam Benger and Katrina Ligett
Published in:
International Conference on Machine Learning (ICML 2026), 2026
Publisher:
PMLR
DOI:
10.48550/ARXIV.2602.07285
Mapping the Tradeoffs and Limitations of Algorithmic Fairness
(opens in new window)
Author(s):
Etam Benger and Katrina Ligett
Published in:
Symposium on Foundations of Responsible Computing (FORC), 2025
Publisher:
LIPIcs
DOI:
10.4230/LIPICS.FORC.2025.19
Near-optimal private linear regression via iterative hessian mixing
(opens in new window)
Author(s):
Omri Lev, Moshe Shenfeld, Vishwak Srinivasan, Katrina Ligett, Ashia C Wilson
Published in:
Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), 2026
Publisher:
PMLR
DOI:
10.48550/ARXIV.2601.07545
How Well Can Differential Privacy Be Audited in One Run?
(opens in new window)
Author(s):
Amit Keinan, Moshe Shenfeld, Katrina Ligett
Published in:
Advances in Neural Information Processing Systems 38, 2025
Publisher:
Neural Information Processing Systems Foundation, Inc. (NeurIPS)
DOI:
10.52202/085713-1632
Efficient privacy loss accounting for subsampling and random allocation
(opens in new window)
Author(s):
Vitaly Feldman, Moshe Shenfeld
Published in:
Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), 2026
Publisher:
PMLR
DOI:
10.48550/ARXIV.2602.17284
