Search Results for author: Sadaf Salehkalaibar

Found 4 papers, 1 papers with code

Rate-Distortion-Perception Tradeoff Based on the Conditional-Distribution Perception Measure

no code implementations22 Jan 2024 Sadaf Salehkalaibar, Jun Chen, Ashish Khisti, Wei Yu

We derive the RDP function for vector Gaussian sources and propose a waterfilling type solution.

M22: A Communication-Efficient Algorithm for Federated Learning Inspired by Rate-Distortion

no code implementations23 Jan 2023 Yangyi Liu, Stefano Rini, Sadaf Salehkalaibar, Jun Chen

This paper proposes ``\emph{${\bf M}$-magnitude weighted $L_{\bf 2}$ distortion + $\bf 2$ degrees of freedom''} (M22) algorithm, a rate-distortion inspired approach to gradient compression for federated training of deep neural networks (DNNs).

Federated Learning

Lossy Gradient Compression: How Much Accuracy Can One Bit Buy?

1 code implementation6 Feb 2022 Sadaf Salehkalaibar, Stefano Rini

Under this assumption on the DNN gradient distribution, we propose a class of distortion measures to aid the design of quantizers for the compression of the model updates.

Federated Learning

Towards Multi-Domain Single Image Dehazing via Test-Time Training

no code implementations CVPR 2022 Huan Liu, Zijun Wu, Liangyan Li, Sadaf Salehkalaibar, Jun Chen, Keyan Wang

Motivated by this observation, we propose a test-time training method which leverages a helper network to assist the dehazing model in better adapting to a domain of interest.

Image Dehazing Meta-Learning +1

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