Several post-training quantization methods have been applied to large
la...
Privacy-Preserving machine learning (PPML) can help us train and deploy
...
We consider private federated learning (FL), where a server aggregates
d...
Differentially Private methods for training Deep Neural Networks (DNNs) ...
Federated Learning (FL) is a setting for training machine learning model...
Reconstruction attacks allow an adversary to regenerate data samples of ...
Neural networks with the Rectified Linear Unit (ReLU) nonlinearity are
d...
We design a family of image classification architectures that optimize t...
To unlock video chat for hundreds of millions of people hindered by poor...
We tackle the problem of producing compact models, maximizing their accu...
We tackle the problem of producing compact models, maximizing their accu...
In this paper, we address the problem of reducing the memory footprint o...
Modern neural networks are over-parametrized. In particular, each rectif...
ConvNets and Imagenet have driven the recent success of deep learning fo...