3 papers
cs.CL2024
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Chulin Xie, Zinan Lin, Arturs Backurs +9
Text data has become extremely valuable due to the emergence of machine learning algorithms that learn from it. A lot of high-quality text data generated in the real world is priva…
cs.LG2024
The Power of Sampling: Dimension-free Risk Bounds in Private ERM
Yin Tat Lee, Daogao Liu, Zhou Lu
Differentially private empirical risk minimization (DP-ERM) is a fundamental problem in private optimization. While the theory of DP-ERM is well-studied, as large-scale models beco…
cs.DS2024
Improving the Bit Complexity of Communication for Distributed Convex Optimization
Mehrdad Ghadiri, Yin Tat Lee, Swati Padmanabhan +3
We consider the communication complexity of some fundamental convex optimization problems in the point-to-point (coordinator) and blackboard communication models. We strengthen kno…