Ujwal Pandey

Ujwal Pandey

Auto-generated profile, based on publicly available information

Ujwal Pandey

Rensselaer Polytechnic Institute

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 February 2024
Verified
Book Chapter
Closed access
PDF file
CBChristopher Brissette
Christopher Brissette
UPUjwal Pandey
Ujwal Pandey
GSGeorge M. Slota
George M. Slota

7 August 2025 in arXiv
Verified
Preprint
Open access
PDF file
WLWei Liu
Wei Liu
APAnweshit Panda
Anweshit Panda
UPUjwal Pandey
Ujwal Pandey
CBChristopher Brissette
Christopher Brissette
YSYikang Shen
Yikang Shen
YXYangyang Xu
Yangyang Xu
In this paper, we design two compressed decentralized algorithms for solving nonconvex stochastic optimization under two different scenarios. Both algorithms adopt a momentum technique to achieve fast convergence and a message-compression technique to save communication costs. Though momentum acceleration and compressed communication have been used in literature, it is highly nontrivial to theoretically prove the effectiveness of their composition in a decentralized algorithm that can maintain the benefits of both sides, because of the need to simultaneously control the consensus error, the compression error, and the bias from the momentum gradient. For the scenario where gradients are bounded, our proposal is a compressed decentralized adaptive method. To the best of our knowledge, this is the first decentralized adaptive stochastic gradient method with compressed communication. For the scenario of data heterogeneity without bounded gradients, our proposal is a compressed decentralized heavy-ball method, which applies a gradient tracking technique to address the challenge of data heterogeneity. Notably, both methods achieve an optimal convergence rate, and they can achieve linear speed up and adopt topology-independent algorithmic parameters within a certain regime of the user-specified error tolerance. Superior empirical performance is observed over state-of-the-art methods on training deep neural networks (DNNs) and Transformers.