Private Algorithms with Minimal Space

Private Algorithms with Minimal Space

Channel:
United States Google TechTalks
Subscribers:
348,000
Published on ● Video Link: https://www.youtube.com/watch?v=IvSrEXAhNL4


Duration: 18:52
413 views
6

A Google TechTalk, 2020/7/29, presented by Adam Smith, Boston University
ABSTRACT: We show that a classic algorithm for counting distinct elements in small space is differentially private with only small modifications. The result is an algorithm with the same space guarantee as in the nonprivate setting, and only an small additional additive error.



Other Videos By Google TechTalks


2021-09-29A Geometric View on Private Gradient-Based Optimization
2021-09-29BB84: Quantum Protected Cryptography
2021-09-29Fast and Memory Efficient Differentially Private-SGD via JL Projections
2021-09-29Leveraging Public Data for Practical Synthetic Data Generation
2021-07-13Efficient Exploration in Bayesian Optimization – Optimism and Beyond by Andreas Krause
2021-07-13Learning to Explore in Molecule Space by Yoshua Bengio
2021-07-13Resource Allocation in Multi-armed Bandits by Kirthevasan Kandasamy
2021-07-13Grey-box Bayesian Optimization by Peter Frazier
2021-06-10Is There a Mathematical Model of the Mind? (Panel Discussion)
2021-06-04Dataset Poisoning on the Industrial Scale
2021-06-04Private Algorithms with Minimal Space
2021-06-04Adaptive Federated Optimization
2021-06-04Orchard: Differentially Private Analytics at Scale
2021-06-04Google Workshop on Federated Learning and Analytics: Talks from Google
2021-06-04Generative Models for Effective ML on Private, Decentralized Datasets
2021-06-04Learning discrete distributions: User vs item-level privacy
2021-06-04TensorFlow Federated Tutorial Session
2021-06-04Learning on Large-Scale Data with Security & Privacy
2021-06-04Attack of the Tails: Yes, you Really can Backdoor Federated Learning
2021-06-04FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning
2021-06-04Profile-based Privacy for Locally Private Computations