Google TechTalks
Google TechTalks — 292 videos with subtitlesGoogle TechTalks has 292 videos indexed on WinkLingo (channel with 349K subscribers). Every video is searchable word by word.
Google Tech Talks is a grass-roots program at Google for sharing information of interest to the technical community. At its best, it's part of an ongoing discussion about our world featuring top experts in diverse fields. Presentations range from the broadest of perspective overviews to the most technical of deep dives, on topics well-established to wildly speculative. Disclaimer: Google TechTalks are designed to disseminate a wide spectrum of views on topics including Current Affairs, Science, Medicine, Engineering, Business, Humanities, Law, Entertainment, and the Arts. The views or…
Recent videos
9:24Information-Constrained Optimization: Can Adaptive Processing of Gradients Help?
10:21Differential privacy dynamics of noisy gradient descent
10:01Consistent Spectral Clustering of Network Block Models under Local Differential Privacy
10:08The Skellam Mechanism for Differentially Private Federated Learning
4:52Statistical Heterogeneity in Federated Learning
10:16Improved Information Theoretic Generalization Bounds for Distributed and Federated Learning
4:10Tight Accounting in the Shuffle Model of Differential Privacy
7:06Distributed Point Functions: Efficient Secure Aggregation and Beyond with Non-Colluding Servers
15:34How to Turn Privacy ON and OFF and ON Again
10:30Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
9:45Secure Federated Learning on Wimpy Devices
12:39Gaps between FL optimization theory and practice
5:20Mistify: Automating DNN Model Porting for On-Device Inference at the Edge
7:33Personalized Graph-Aided Online Federated Model Selection
9:11Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase Transition
8:35Distributed neural network training via independent subnets
5:56Locally Differentially Private Bayesian Inference
10:15Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients
5:54SparseFed: Mitigation Model Poisoning Attacks in Federated Learning with Sparsification
16:58Federated Multi-Task Learning under a Mixture of Distributions
10:20Private Multi-Group Aggregation
10:30Private Goodness-of-Fit: A Few Ideas Go a Long Way
5:51Privacy Amplification by Decentralization
11:46Experimenting w/ Local & Central Differential Privacy for Both Robustness & Privacy in Fed.Learning