Video quality assessment (VQA) has attracted growing attention in recent...
Video Quality Assessment (VQA), which aims to predict the perceptual qua...
Recent advancements in surgical computer vision applications have been d...
This paper reports on the NTIRE 2023 Quality Assessment of Video Enhance...
Federated learning is a powerful paradigm for large-scale machine learni...
Decentralized Stochastic Gradient Descent (SGD) is an emerging neural ne...
Communication compression is a common technique in distributed optimizat...
Communication compression is an essential strategy for alleviating
commu...
Video quality assessment (VQA) aims to simulate the human perception of ...
While most recent autonomous driving system focuses on developing percep...
Blind image quality assessment (BIQA) aims to automatically evaluate the...
Formalizing surgical activities as triplets of the used instruments, act...
Decentralized optimization with time-varying networks is an emerging par...
Decentralized optimization is an emerging paradigm in distributed learni...
Decentralized optimization is effective to save communication in large-s...
We study the decentralized optimization problem where a network of n age...
Recent advances in distributed optimization and learning have shown that...
Recent theoretical studies have shown that heavy-tails can emerge in
sto...
Face inpainting aims to complete the corrupted regions of the face image...
Person image generation aims to perform non-rigid deformation on source
...
Decentralized algorithm is a form of computation that achieves a global ...
Decentralized SGD is an emerging training method for deep learning known...
We study the consensus decentralized optimization problem where the obje...
Decentralized optimization and communication compression have exhibited ...
Communication overhead hinders the scalability of large-scale distribute...
We consider decentralized stochastic optimization problems where a netwo...
When applying a stochastic/incremental algorithm, one must choose the or...
The scale of deep learning nowadays calls for efficient distributed trai...
In this paper we propose a novel network adaption method called
Differen...
Motivated by the success of Transformers in natural language processing ...
Sparsity in Deep Neural Networks (DNNs) has been widely studied to compr...
One practice of employing deep neural networks is to apply the same
arch...
Seeking effective neural networks is a critical and practical field in d...
Despite remarkable empirical success, the training dynamics of generativ...
Decentralized optimization is a promising paradigm that finds various
ap...
Various bias-correction methods such as EXTRA, DIGing, and exact diffusi...
This work derives and analyzes an online learning strategy for tracking ...
This work develops a fully decentralized multi-agent algorithm for polic...
In this paper we develop a fully decentralized algorithm for policy
eval...
This work studies the problem of learning under both large data and larg...
This paper addresses consensus optimization problems in a multi-agent
ne...
This paper addresses consensus optimization problem in a multi-agent net...
In empirical risk optimization, it has been observed that stochastic gra...
This work develops a fully decentralized variance-reduced learning algor...
Several useful variance-reduced stochastic gradient algorithms, such as ...
The article examines in some detail the convergence rate and
mean-square...
The stochastic dual coordinate-ascent (S-DCA) technique is a useful
alte...