Google TechTalks
Google TechTalks · 292 个带字幕的视频Google TechTalks 在 WinkLingo 收录了 292 个视频(这个频道有 35万 个订阅),每个视频都能逐词检索。
查看 YouTube 原频道英文简介
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…
收录的视频
9:24信息约束优化:梯度自适应处理能提供帮助吗?
Information-Constrained Optimization: Can Adaptive Processing of Gradients Help?
10:21噪声梯度下降的差分隐私动态
Differential privacy dynamics of noisy gradient descent
10:01局部差分隐私下网络块模型的鲁棒谱聚类
Consistent Spectral Clustering of Network Block Models under Local Differential Privacy
10:08用于差分隐私联邦学习的 Skellam 机制
The Skellam Mechanism for Differentially Private Federated Learning
4:52联邦学习中的统计异质性
Statistical Heterogeneity in Federated Learning
10:16分布式与联邦学习中改进的信息论泛化界限
Improved Information Theoretic Generalization Bounds for Distributed and Federated Learning
4:10差分隐私 Shuffle 模型中的紧凑会计方法
Tight Accounting in the Shuffle Model of Differential Privacy
7:06分布式点函数:利用非共谋服务器实现高效的安全聚合及更多应用
Distributed Point Functions: Efficient Secure Aggregation and Beyond with Non-Colluding Servers
15:34如何开关隐私设置:从关闭到开启的完整指南
How to Turn Privacy ON and OFF and ON Again
10:30基于有序丢弃在异构目标下的公平且准确的联邦学习
Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
9:45在低功耗设备上实现安全的联邦学习
Secure Federated Learning on Wimpy Devices
12:39FL(联邦学习)优化理论与实践之间的差距
Gaps between FL optimization theory and practice
5:20Mistify:自动化 DNN 模型移植以实现边缘设备端推理
Mistify: Automating DNN Model Porting for On-Device Inference at the Edge
7:33个性化图辅助在线联邦模型选择
Personalized Graph-Aided Online Federated Model Selection
9:11每用户多样本的分布式估计:锐率与相变
Distributed Estimation with Multiple Samples per User: Sharp Rates and Phase Transition
8:35通过独立子网进行分布式神经网络训练
Distributed neural network training via independent subnets
5:56局部差分隐私贝叶斯推理
Locally Differentially Private Bayesian Inference
10:15联邦学习中的线性收敛:解决客户端异构性和稀疏梯度问题
Linear Convergence in Federated Learning: Tackling Client Heterogeneity and Sparse Gradients
5:54SparseFed:通过稀疏化缓解联邦学习中的模型中毒攻击
SparseFed: Mitigation Model Poisoning Attacks in Federated Learning with Sparsification
16:58分布混合模型下的联邦多任务学习
Federated Multi-Task Learning under a Mixture of Distributions
10:20私有多组聚合 (Private Multi-Group Aggregation)
Private Multi-Group Aggregation
10:30私有拟合优度:几个简单想法的深远影响
Private Goodness-of-Fit: A Few Ideas Go a Long Way
5:51通过去中心化增强隐私
Privacy Amplification by Decentralization
11:46在联邦学习中实验局部与中心差分隐私,以兼顾鲁棒性与隐私
Experimenting w/ Local & Central Differential Privacy for Both Robustness & Privacy in Fed.Learning