Differentially Private Set Union
Jul 12, 2020
Speakers
Sivakanth Gopi
Speaker · 0 followers
Pankaj Gulhane
Speaker · 0 followers
Janardhan Kulkarni
Speaker · 0 followers
Judy Hanwen Shen
Speaker · 0 followers
Milad Shokouhi
Speaker · 0 followers
Sergey Yekhanin
Speaker · 0 followers
About
We study the basic operation of set union in the global model of differential privacy. In this problem, we are given a universe U of items, possibly of infinite size, and a database D of users. Each user i contributes a subset W_i ⊆ U of items. We want an (ϵ,δ)-differentially private Algorithm which outputs a subset S ⊂∪_i W_i such that the size of S is as large as possible. The problem arises in countless real world applications, and is particularly important and ubiquitous in natural language processing (NLP) problems. For example, discovering words, sentences, n-grams etc., from private text data belonging to users is an instance of the set union problem. Known algorithms for this problem proceed by collecting a (weighted) subset of items from each user, taking the union of such subsets, and disclosing the items whose noisy counts fall above a certain cutoff threshold. Crucially, in the above process, the contribution of each individual user is always independent from identity of items held by other users, resulting in a wasteful aggregation process, where some items’ counts happen to be very large – far above the cutoff threshold. We deviate from the above paradigm, by allowing users to contribute their items in a dependent fashion, guided by a policy. In this new setting ensuring privacy is significantly delicate. We prove that any policy which has certain contractive properties would result in a differentially private algorithm. We design two new algorithms, one using Laplace Noise and other Gaussian noise, as specific instances of policies satisfying the contractive properties. Our experiments show that the new algorithms significantly outperform previously known mechanisms for the problem.We study the basic operation of set union in the global model of differential privacy. In this problem, we are given a universe U of items, possibly of infinite size, and a database D of users. Each user i contributes a subset W_i ⊆ U of items. We want an (ϵ,δ)-differentially private Algorithm which outputs a subset S ⊂∪_i W_i such that the size of S is as large as possible. The problem arises in countless real world applications, and is particularly important and ubiquitous in natural language…
Categories
Web Development & UX/UI
Category · 1.2k presentations
AI & Data Science
Category · 10.8k presentations
App & Game Development
Category · 954 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
ControlVAE: Controllable Variational Autoencoder
Watch later
Huajie Shao, …
Simple and Deep Graph Convolutional Networks
Watch later
Ming Chen, …
Kernel interpolation with continuous volume sampling
Watch later
Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks
Watch later
David Stutz, …
Priors for System 2 Knowledge Representation
Watch later
