Agnostic Federated Learning,解决之前联邦学习机制中会对某些客户端任务发生倾斜的问题; Bayesian Nonparametric Federated Learning of Neural Networks. ICML 2019. 提出单样本/少样本探索式的学习方法来解决通信问题; Protection Against Reconstruction and Its Applications in Private Federated Learning,提出了一种差异性...
[21] Kernel-Based Reinforcement Learning in Robust Markov Decision Processes Paper:http://proceedings.mlr.press/v97/lim19a/lim19a.pdf Resource:https://github.com/shonglim/icml2019 [22] Taming MAML: Efficient unbiased meta-reinforcement learning Paper:http://proceedings.mlr.press/v97/liu19g/liu19...
Agnostic Federated LearningMehryar Mohri, Gary Sivek, Ananda Theertha SureshCategorical Feature Compression via Submodular OptimizationMohammad Hossein Bateni, Lin Chen, Hossein Esfandiari, Thomas Fu, Vahab Mirrokni, Afshin RostamizadehCross-Domain 3D Equivariant Image EmbeddingsCarlos Esteves, Avneesh Sud, ...
In Exploring Weight Agnostic Neural Networks , we showed how it is possible to find interesting neural network architectures without any training steps to update the weights of the evaluated models. This can make architecture search much more computationally efficient. A weight-agnostic neural network ...
A weight-agnostic neural network performing a Cartpole Swing-up task at various different weight parameters, and also using fine-tuned weight parameters. Applying AutoML to Transformer Architecturesexplored finding architectures for natural language processing tasks that significantly outperform vanilla Transform...
ICML:约200名Google员工发表了100多篇论文、演讲、海报、研讨会等。 ICLR:约200名Google员工发表了60多篇论文、演讲、海报、研讨会等。 ACL:约100位Google员工发表了40多篇论文、研讨会和教程。 Interspeech: 100多位Google员工发表了30多篇论文。 ICCV:约200名Google员工发表了40多篇论文,还有几位Google员工还获得...