Author name cluster

Jemin George

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

NeurIPS Conference 2020 Conference Paper

Decentralized Langevin Dynamics for Bayesian Learning

Anjaly Parayil
He Bai
Jemin George
Prudhvi Gurram

Motivated by decentralized approaches to machine learning, we propose a collaborative Bayesian learning algorithm taking the form of decentralized Langevin dynamics in a non-convex setting. Our analysis show that the initial KL-divergence between the Markov Chain and the target posterior distribution is exponentially decreasing while the error contributions to the overall KL-divergence from the additive noise is decreasing in polynomial time. We further show that the polynomial-term experiences speed-up with number of agents and provide sufficient conditions on the time-varying step-sizes to guarantee convergence to the desired distribution. The performance of the proposed algorithm is evaluated on a wide variety of machine learning tasks. The empirical results show that the performance of individual agents with locally available data is on par with the centralized setting with considerable improvement in the convergence rate.

PDF Details

AAAI Conference 2020 Conference Paper

Distributed Stochastic Gradient Descent with Event-Triggered Communication

Jemin George
Prudhvi Gurram

We develop a Distributed Event-Triggered Stochastic GRAdient Descent (DETSGRAD) algorithm for solving non-convex optimization problems typically encountered in distributed deep learning. We propose a novel communication triggering mechanism that would allow the networked agents to update their model parameters aperiodically and provide suf- ﬁcient conditions on the algorithm step-sizes that guarantee the asymptotic mean-square convergence. The algorithm is applied to a distributed supervised-learning problem, in which a set of networked agents collaboratively train their individual neural networks to perform image classiﬁcation, while aperiodically sharing the model parameters with their onehop neighbors. Results indicate that all agents report similar performance that is also comparable to the performance of a centrally trained neural network, while the event-triggered communication provides signiﬁcant reduction in inter-agent communication. Results also show that the proposed algorithm allows the individual agents to classify the images even though the training data corresponding to all the classes are not locally available to each agent.

PDF Details