13 citations · 33 across the 8 of their papers we have counts for
10 papers
Alternating Mahalanobis Distance Minimization for Stable and Accurate CP Decomposition
Navjot Singh, Edgar Solomonik
CP decomposition (CPD) is prevalent in chemometrics, signal processing, data mining and many more fields. While many algorithms have been proposed to compute the CPD, alternating l…
QuPeD: Quantized Personalization via Distillation with Applications to Federated Learning
Kaan Ozkara, Navjot Singh, Deepesh Data +1
Traditionally, federated learning (FL) aims to train a single global model while collaboratively using multiple clients and a server. Two natural challenges that FL algorithms face…
MTC: Multiresolution Tensor Completion from Partial and Coarse Observations
Chaoqi Yang, Navjot Singh, Cao Xiao +3
Existing tensor completion formulation mostly relies on partial observations from a single tensor. However, tensors extracted from real-world data are often more complex due to: (i…
QuPeL: Quantized Personalization with Applications to Federated Learning
Kaan Ozkara, Navjot Singh, Deepesh Data +1
Traditionally, federated learning (FL) aims to train a single global model while collaboratively using multiple clients and a server. Two natural challenges that FL algorithms face…
SQuARM-SGD: Communication-Efficient Momentum SGD for Decentralized Optimization
Navjot Singh, Deepesh Data, Jemin George +1
In this paper, we propose and analyze SQuARM-SGD, a communication-efficient algorithm for decentralized training of large-scale machine learning models over a network. In SQuARM-SG…
SPARQ-SGD: Event-Triggered and Compressed Communication in Decentralized Stochastic Optimization
Navjot Singh, Deepesh Data, Jemin George +1
In this paper, we propose and analyze SPARQ-SGD, which is an event-triggered and compressed algorithm for decentralized training of large-scale machine learning models. Each node c…