Differentially Private Set Union
12. července 2020
Řečníci
Sivakanth Gopi
Řečník · 0 sledujících
Pankaj Gulhane
Řečník · 0 sledujících
Janardhan Kulkarni
Řečník · 0 sledujících
Judy Hanwen Shen
Řečník · 0 sledujících
Milad Shokouhi
Řečník · 0 sledujících
Sergey Yekhanin
Řečník · 0 sledujících
O prezentaci
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…
Kategorie
Vývoj webu a UX/UI
Kategorie · 1,2k prezentací
Umělá inteligence a data science
Kategorie · 10,8k prezentací
Vývoj aplikací a her
Kategorie · 954 prezentací
O organizátorovi (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.
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Opening remarks
Zhlédnout později
From Chaos to Order: Symmetry and Conservation Laws in Game Dynamics
Zhlédnout později
Optimal Continual Learning has Perfect Memory and is NP-hard
Zhlédnout později
Invited Talk 2 Q&A
Zhlédnout později
Understanding and Stabilizing GANs' Training Dynamics Using Control Theory
Zhlédnout později
Chongxuan Li, …
PowerNorm: Rethinking Batch Normalization in Transformers
Zhlédnout později
Sheng Shen, …