Inverting Gradients - How easy is it to break privacy in federated learning?
6. prosince 2020
Řečníci
Jonas Geiping
Speaker · 0 followers
Hartmut Bauermeister
Speaker · 0 followers
Hannah Dröge
Speaker · 0 followers
Michael Moeller
Speaker · 0 followers
Organizátor
NeurIPS 2020
Account · 11.7k followers
Kategorie
AI & Data Science
Category · 10.8k presentations
Computer Systems & Networks
Category · 423 presentations
O organizátorovi (NeurIPS 2020)
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
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
Towards Problem-dependent Optimal Learning Rates
Watch later
Yunbei Xu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Simplify and Robustify Negative Sampling for Implicit Collaborative Filtering
Watch later
Jingtao Ding, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Throughput-Optimal Topology Design for Cross-Silo Federated Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Optimal Lottery Tickets via SubsetSum: Logarithmic Over-Parameterization is Sufficient
Watch later
Ankit Pensia, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Kernel Alignment Risk Estimator: Risk Prediction from Training Data
Watch later
Arthur Jacot, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Neural Star Domain as Primitive Representation
Watch later
Yuki Kawana, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%