activity
20192021
most citedOn Higher-order Moments in Adam

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG2021

Granger Causality Based Hierarchical Time Series Clustering for State Estimation

Sin Yong Tan, Homagni Saha, Margarite Jacoby +2

Clustering is an unsupervised learning technique that is useful when working with a large volume of unlabeled data. Complex dynamical systems in real life often entail data streami…

cs.LG2021

Cross-Gradient Aggregation for Decentralized Learning from Non-IID data

Yasaman Esfandiari, Sin Yong Tan, Zhanhong Jiang +4

Decentralized learning enables a group of collaborative agents to learn models using a distributed dataset without the need for a central parameter server. Recently, decentralized…

cs.LG2020

Decentralized Deep Learning using Momentum-Accelerated Consensus

Aditya Balu, Zhanhong Jiang, Sin Yong Tan +3

We consider the problem of decentralized deep learning where multiple agents collaborate to learn from a distributed dataset. While there exist several decentralized deep learning…

cs.CV2020

Few shot clustering for indoor occupancy detection with extremely low-quality images from battery free cameras

Homagni Saha, Sin Yong Tan, Ali Saffari +3

Reliable detection of human occupancy in indoor environments is critical for various energy efficiency, security, and safety applications. We consider this challenge of occupancy d…

cs.LG2020

Spatiotemporal Attention for Multivariate Time Series Prediction and Interpretation

Tryambak Gangopadhyay, Sin Yong Tan, Zhanhong Jiang +2

Multivariate time series modeling and prediction problems are abundant in many machine learning application domains. Accurate interpretation of such prediction outcomes from a mach…

cs.LG20191 cited

On Higher-order Moments in Adam

Zhanhong Jiang, Aditya Balu, Sin Yong Tan +3

In this paper, we investigate the popular deep learning optimization routine, Adam, from the perspective of statistical moments. While Adam is an adaptive lower-order moment based…