111 citations · 338 across the 50 of their papers we have counts for
7 papers · 2 filters
Parallel Restarted SPIDER -- Communication Efficient Distributed Nonconvex Optimization with Optimal Computation Complexity
Pranay Sharma, Swatantra Kafle, Prashant Khanduri +3
In this paper, we propose a distributed algorithm for stochastic smooth, non-convex optimization. We assume a worker-server architecture where nodes, each having (potential…
Nonstationary Nonparametric Online Learning: Balancing Dynamic Regret and Model Parsimony
Amrit Singh Bedi, Alec Koppel, Ketan Rajawat +1
An open challenge in supervised learning is \emph{conceptual drift}: a data point begins as classified according to one label, but over time the notion of that label changes. Beyon…
Adaptive Kernel Learning in Heterogeneous Networks
Hrusikesha Pradhan, Amrit Singh Bedi, Alec Koppel +1
We consider learning in decentralized heterogeneous networks: agents seek to minimize a convex functional that aggregates data across the network, while only having access to their…
Distributed Inexact Successive Convex Approximation ADMM: Analysis-Part I
Sandeep Kumar, Ketan Rajawat, Daniel P. Palomar
In this two-part work, we propose an algorithmic framework for solving non-convex problems whose objective function is the sum of a number of smooth component functions plus a conv…
Online Learning over Dynamic Graphs via Distributed Proximal Gradient Algorithm
Rishabh Dixit, Amrit Singh Bedi, Ketan Rajawat
We consider the problem of tracking the minimum of a time-varying convex optimization problem over a dynamic graph. Motivated by target tracking and parameter estimation problems i…
Escaping Saddle Points with the Successive Convex Approximation Algorithm
Amrit Singh Bedi, Ketan Rajawat, Vaneet Aggarwal
Optimizing non-convex functions is of primary importance in the vast majority of machine learning algorithms. Even though many gradient descent based algorithms have been studied,…