Optimal Differential Privacy Composition for Exponential Mechanisms
Jul 12, 2020
Speakers
Jinshuo Dong
Speaker · 0 followers
David Durfee
Speaker · 0 followers
Ryan Rogers
Speaker · 0 followers
About
Composition is one of the most important properties of differential privacy (DP), as it allows algorithm designers to build complex private algorithms from DP primitives. We consider precise composition bounds of the overall privacy loss for exponential mechanisms, one of the fundamental classes of mechanisms in DP. Exponential mechanism has also become a fundamental building block in private machine learning, e.g. private PCA and hyper-parameter selection. We give explicit formulations of the optimal privacy loss for both the adaptive and non-adaptive composition of exponential mechanism. For the non-adaptive setting in which each mechanism has the same privacy parameter, we give an efficiently computable formulation of the optimal privacy loss. In the adaptive case, we derive a recursive formula and an efficiently computable upper bound. These precise understandings about the problem lead to a 40% saving of the privacy budget in a practical application. Furthermore, the algorithm-specific analysis shows a difference in privacy parameters of adaptive and non-adaptive composition, which was widely believed to not exist based on the evidence from general analysis.Composition is one of the most important properties of differential privacy (DP), as it allows algorithm designers to build complex private algorithms from DP primitives. We consider precise composition bounds of the overall privacy loss for exponential mechanisms, one of the fundamental classes of mechanisms in DP. Exponential mechanism has also become a fundamental building block in private machine learning, e.g. private PCA and hyper-parameter selection. We give explicit formulations of the o…
Categories
Mathematics
Category · 2.4k presentations
Visual Arts & Graphic Design
Category · 333 presentations
AI & Data Science
Category · 10.8k presentations
About ICML 2020
The International Conference on Machine Learning (ICML) is the premier gathering of professionals dedicated to the advancement of the branch of artificial intelligence known as machine learning. ICML is globally renowned for presenting and publishing cutting-edge research on all aspects of machine learning used in closely related areas like artificial intelligence, statistics and data science, as well as important application areas such as machine vision, computational biology, speech recognition, and robotics. ICML is one of the fastest growing artificial intelligence conferences in the world. Participants at ICML span a wide range of backgrounds, from academic and industrial researchers, to entrepreneurs and engineers, to graduate students and postdocs.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
DINO: Distributed Newton-Type Optimization Method
Watch later
Rixon Crane, …
Supermasks in Superposition
Watch later
Overfitting in adversarially robust deep learning
Watch later
Leslie Rice, …
What Does It Mean for Machine Learning to Be Trustworthy?
Watch later
A Chance-Constrained Generative Framework for Sequence Optimization
Watch later
Jian Peng, …