research
∙
05/29/2023
LLM-QAT: Data-Free Quantization Aware Training for Large Language Models
Several post-training quantization methods have been applied to large la...
share
research
∙
05/22/2023
EXACT: Extensive Attack for Split Learning
Privacy-Preserving machine learning (PPML) can help us train and deploy ...
research
∙
11/08/2022
The Interpolated MVU Mechanism For Communication-efficient Private Federated Learning
We consider private federated learning (FL), where a server aggregates d...
research
∙
10/07/2022
TAN without a burn: Scaling Laws of DP-SGD
Differentially Private methods for training Deep Neural Networks (DNNs) ...
research
∙
10/06/2022
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
Federated Learning (FL) is a setting for training machine learning model...
research
∙
02/15/2022
Defending against Reconstruction Attacks with Rényi Differential Privacy
Reconstruction attacks allow an adversary to regenerate data samples of ...
research
∙
07/20/2021
An Embedding of ReLU Networks and an Analysis of their Identifiability
Neural networks with the Rectified Linear Unit (ReLU) nonlinearity are d...
research
∙
04/02/2021
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference
We design a family of image classification architectures that optimize t...
research
∙
12/01/2020
Low Bandwidth Video-Chat Compression using Deep Generative Models
To unlock video chat for hundreds of millions of people hindered by poor...
research
∙
04/15/2020
Training with Quantization Noise for Extreme Model Compression
We tackle the problem of producing compact models, maximizing their accu...
research
∙
04/15/2020
Training with Quantization Noise for Extreme Fixed-Point Compression
We tackle the problem of producing compact models, maximizing their accu...
research
∙
07/12/2019
And the Bit Goes Down: Revisiting the Quantization of Neural Networks
In this paper, we address the problem of reducing the memory footprint o...
research
∙
02/27/2019
Equi-normalization of Neural Networks
Modern neural networks are over-parametrized. In particular, each rectif...
research
∙
11/30/2017