11 citations · 18 across the 10 of their papers we have counts for
17 papers
On Self-Adaptive Perception Loss Function for Sequential Lossy Compression
Sadaf Salehkalaibar, Buu Phan, Likun Cai +4
We consider causal, low-latency, sequential lossy compression, with mean squared-error (MSE) as the distortion loss, and a perception loss function (PLF) to enhance the realism of…
Rate-Distortion-Perception Tradeoff for Gaussian Vector Sources
Jingjing Qian, Sadaf Salehkalaibar, Jun Chen +5
This paper studies the rate-distortion-perception (RDP) tradeoff for a Gaussian vector source coding problem where the goal is to compress the multi-component source subject to dis…
Rate-Distortion-Perception Tradeoff Based on the Conditional-Distribution Perception Measure
Sadaf Salehkalaibar, Jun Chen, Ashish Khisti +1
This paper studies the rate-distortion-perception (RDP) tradeoff for a memoryless source model in the asymptotic limit of large block-lengths. The perception measure is based on a…
On the Choice of Perception Loss Function for Learned Video Compression
Sadaf Salehkalaibar, Buu Phan, Jun Chen +2
We study causal, low-latency, sequential video compression when the output is subjected to both a mean squared-error (MSE) distortion loss as well as a perception loss to target re…
M22: A Communication-Efficient Algorithm for Federated Learning Inspired by Rate-Distortion
Yangyi Liu, Stefano Rini, Sadaf Salehkalaibar +1
In federated learning (FL), the communication constraint between the remote learners and the Parameter Server (PS) is a crucial bottleneck. For this reason, model updates must be c…
Lossy Gradient Compression: How Much Accuracy Can One Bit Buy?
Sadaf Salehkalaibar, Stefano Rini
In federated learning (FL), a global model is trained at a Parameter Server (PS) by aggregating model updates obtained from multiple remote learners. Generally, the communication b…