Oracle-Efficient Differentially Private Learning with Public Data

Authors: Adam Block, Mark Bun, Rathin Desai, Abhishek Shetty, Steven Z. Wu

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this work, we present the first computationally efficient, algorithms to provably leverage public data to learn privately whenever a function class is learnable non-privately, where our notion of computational efficiency is with respect to the number of calls to an optimization oracle for the function class. In this section, we outline the proofs of our main results, with full details deferred to Appendix C.
Researcher Affiliation Academia Adam Block Department of Mathematics MIT Cambridge, MA 02139 ablock@mit.edu Mark Bun Department of Computer Science Boston University Boston, MA 02215 mbun@bu.edu Rathin Desai Department of Computer Science Boston University Boston, MA 02215 rathin@bu.edu Abhishek Shetty Department of Computer Science University of California, Berkeley Berkeley, CA 94720 shetty@berkeley.edu Zhiwei Steven Wu School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 zstevenwu@cmu.edu
Pseudocode Yes Algorithm 1: Perturb: An algorithm for perturbing a function with noise on public data.
Open Source Code No The paper does not contain any statement or link indicating the release of source code for the described methodology.
Open Datasets No The paper discusses theoretical concepts of "private samples" and "unlabeled public samples" from distributions, but does not refer to specific, publicly available datasets with access information for experimental use.
Dataset Splits No The paper is theoretical and does not describe experimental setups with dataset splits (e.g., training, validation, test).
Hardware Specification No The paper is theoretical and does not describe any specific hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not list any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details such as hyperparameters or system-level training settings.