Search Results for author: Alex Bie

Found 8 papers, 5 papers with code

Parametric Feature Transfer: One-shot Federated Learning with Foundation Models

no code implementations2 Feb 2024 Mahdi Beitollahi, Alex Bie, Sobhan Hemati, Leo Maxime Brunswic, Xu Li, Xi Chen, Guojun Zhang

This paper introduces FedPFT (Federated Learning with Parametric Feature Transfer), a methodology that harnesses the transferability of foundation models to enhance both accuracy and communication efficiency in one-shot FL.

Federated Learning

Understanding the Role of Layer Normalization in Label-Skewed Federated Learning

1 code implementation18 Aug 2023 Guojun Zhang, Mahdi Beitollahi, Alex Bie, Xi Chen

In this work, we reveal the profound connection between layer normalization and the label shift problem in federated learning.

Federated Learning

Private GANs, Revisited

1 code implementation6 Feb 2023 Alex Bie, Gautam Kamath, Guojun Zhang

We show that the canonical approach for training differentially private GANs -- updating the discriminator with differentially private stochastic gradient descent (DPSGD) -- can yield significantly improved results after modifications to training.

Image Generation

Private Estimation with Public Data

1 code implementation16 Aug 2022 Alex Bie, Gautam Kamath, Vikrant Singhal

We initiate the study of differentially private (DP) estimation with access to a small amount of public data.

Don’t Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence

no code implementations NeurIPS 2021 Tianshi Cao, Alex Bie, Arash Vahdat, Sanja Fidler, Karsten Kreis

Generative models trained with privacy constraints on private data can sidestep this challenge, providing indirect access to private data instead.

Don't Generate Me: Training Differentially Private Generative Models with Sinkhorn Divergence

1 code implementation1 Nov 2021 Tianshi Cao, Alex Bie, Arash Vahdat, Sanja Fidler, Karsten Kreis

Generative models trained with privacy constraints on private data can sidestep this challenge, providing indirect access to private data instead.

Differentially Private Generative Models Through Optimal Transport

no code implementations1 Jan 2021 Tianshi Cao, Alex Bie, Karsten Kreis, Sanja Fidler

Generative models trained with privacy constraints on private data can sidestep this challenge and provide indirect access to the private data instead.

A Simplified Fully Quantized Transformer for End-to-end Speech Recognition

4 code implementations9 Nov 2019 Alex Bie, Bharat Venkitesh, Joao Monteiro, Md. Akmal Haidar, Mehdi Rezagholizadeh

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on edge devices.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1

Cannot find the paper you are looking for? You can Submit a new open access paper.