Information-Constrained Optimization: Can Adaptive Processing of Gradients Help?

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


Category:
Guide
Duration: 9:24
698 views
8

A Google TechTalk, presented by Jayadev Acharya, Cornell University, at the 2021 Google Federated Learning and Analytics Workshop, Nov. 8-10, 2021.

For more information about the workshop: https://events.withgoogle.com/2021-workshop-on-federated-learning-and-analytics/#content



Other Videos By Google TechTalks


2022-05-052022 Blockly Developers Summit: Debugging in Blockly
2022-05-052022 Blockly Developers Summit: Year in Review and Roadmap
2022-05-052022 Blockly Developers Summit: Customizing Blockly
2022-05-052022 Blockly Developers Summit: Blockly at Google - Scratch for CS First
2022-05-052022 Blockly Developers Summit: Serialization
2022-05-052022 Blockly Developers Summit: Block Definitions - Past, Present, and Future
2022-05-052022 Blockly Developers Summit: TypeScript Migration
2022-05-052022 Blockly Developers Summit: Contributing to Blockly
2022-05-052022 Blockly Developers Summit: Backwards Execution
2022-02-14Probabilistic Numerics — moving BayesOpt expertise to the inner loop by Philipp Hennig
2022-02-08Information-Constrained Optimization: Can Adaptive Processing of Gradients Help?
2022-02-08Differential privacy dynamics of noisy gradient descent
2022-02-08Consistent Spectral Clustering of Network Block Models under Local Differential Privacy
2022-02-08The Skellam Mechanism for Differentially Private Federated Learning
2022-02-08Statistical Heterogeneity in Federated Learning
2022-02-08Improved Information Theoretic Generalization Bounds for Distributed and Federated Learning
2022-02-08Tight Accounting in the Shuffle Model of Differential Privacy
2022-02-08Distributed Point Functions: Efficient Secure Aggregation and Beyond with Non-Colluding Servers
2022-02-08How to Turn Privacy ON and OFF and ON Again
2022-02-08Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
2022-02-08Secure Federated Learning on Wimpy Devices