5 papers
Smart Information Exchange for Unsupervised Federated Learning via Reinforcement Learning
Seohyun Lee, Anindya Bijoy Das, Satyavrat Wagle +1
One of the main challenges of decentralized machine learning paradigms such as Federated Learning (FL) is the presence of local non-i.i.d. datasets. Device-to-device transfers (D2D…
Preserving Sparsity and Privacy in Straggler-Resilient Distributed Matrix Computations
Anindya Bijoy Das, Aditya Ramamoorthy, David J. Love +1
Existing approaches to distributed matrix computations involve allocating coded combinations of submatrices to worker nodes, to build resilience to stragglers and/or enhance privac…
A Reinforcement Learning-Based Approach to Graph Discovery in D2D-Enabled Federated Learning
Satyavrat Wagle, Anindya Bijoy Das, David J. Love +1
Augmenting federated learning (FL) with direct device-to-device (D2D) communications can help improve convergence speed and reduce model bias through rapid local information exchan…
Coded Matrix Computations for D2D-enabled Linearized Federated Learning
Anindya Bijoy Das, Aditya Ramamoorthy, David J. Love +1
Federated learning (FL) is a popular technique for training a global model on data distributed across client devices. Like other distributed training techniques, FL is susceptible…
On the Design and Analysis of Quaternary Serial and Parallel Adders
Anindya Das, Ifat Jahangir, Masud Hasan
Optimization techniques for decreasing the time and area of adder circuits have been extensively studied for years mostly in binary logic system. In this paper, we provide the nece…