Sai Aparna Aketi

Publication Activity (10 Years)

Years Active: 2018-2024
Publications (10 Years): 25

Top Topics

Heterogeneous Data

Convolutional Neural Networks

Top Venues

Trans. Mach. Learn. Res.

IEEE Trans. Circuits Syst. I Fundam. Theory Appl.

Publications

Sakshi Choudhary, Sai Aparna Aketi, Gobinda Saha, Kaushik Roy
CoDeC: Communication-Efficient Decentralized Continual Learning. Trans. Mach. Learn. Res. 2024 (2024)
Sai Aparna Aketi, Kaushik Roy
Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data. WACV (2024)
Deepak Ravikumar, Gobinda Saha, Sai Aparna Aketi, Kaushik Roy
Homogenizing Non-IID Datasets via In-Distribution Knowledge Distillation for Decentralized Learning. Trans. Mach. Learn. Res. 2024 (2024)
Sai Aparna Aketi, Abolfazl Hashemi, Kaushik Roy
AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression. CoRR (2024)
Timur Ibrayev, Amitangshu Mukherjee, Sai Aparna Aketi, Kaushik Roy
Towards Two-Stream Foveation-based Active Vision Learning. CoRR (2024)
Sai Aparna Aketi, Sakshi Choudhary, Kaushik Roy
Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data. Tiny Papers @ ICLR (2024)
Sakshi Choudhary, Sai Aparna Aketi, Kaushik Roy
SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data. CoRR (2024)
Sai Aparna Aketi, Sakshi Choudhary, Kaushik Roy
Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data. CoRR (2024)
Sakshi Choudhary, Sai Aparna Aketi, Gobinda Saha, Kaushik Roy
CoDeC: Communication-Efficient Decentralized Continual Learning. CoRR (2023)
Sai Aparna Aketi, Kaushik Roy
Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data. CoRR (2023)
Sai Aparna Aketi, Abolfazl Hashemi, Kaushik Roy
Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data. NeurIPS (2023)
Sai Aparna Aketi, Abolfazl Hashemi, Kaushik Roy
Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data. CoRR (2023)
Deepak Ravikumar, Gobinda Saha, Sai Aparna Aketi, Kaushik Roy
Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning. CoRR (2023)
Sai Aparna Aketi, Sangamesh Kodge, Kaushik Roy
Neighborhood Gradient Mean: An Efficient Decentralized Learning Method for Non-IID Data. Trans. Mach. Learn. Res. 2023 (2023)
Sai Aparna Aketi, Sangamesh Kodge, Kaushik Roy
Low precision decentralized distributed training over IID and non-IID data. Neural Networks 155 (2022)
Sai Aparna Aketi, Sangamesh Kodge, Kaushik Roy
Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data Distributions. CoRR (2022)
Sai Aparna Aketi, Sangamesh Kodge, Kaushik Roy
Low Precision Decentralized Distributed Training with Heterogeneous Data. CoRR (2021)
Sai Aparna Aketi, Amandeep Singh, Jan M. Rabaey
Sparse-Push: Communication- & Energy-Efficient Decentralized Distributed Learning over Directed & Time-Varying Graphs with non-IID Datasets. CoRR (2021)
Sai Aparna Aketi, Sourjya Roy, Anand Raghunathan, Kaushik Roy
Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks. CoRR (2020)
Sai Aparna Aketi, Smriti Gupta, Huimei Cheng, Joycee Mekie, Peter A. Beerel
SERAD: Soft Error Resilient Asynchronous Design Using a Bundled Data Protocol. IEEE Trans. Circuits Syst. I Fundam. Theory Appl. (5) (2020)
Sai Aparna Aketi, Sourjya Roy, Anand Raghunathan, Kaushik Roy
Gradual Channel Pruning While Training Using Feature Relevance Scores for Convolutional Neural Networks. IEEE Access 8 (2020)
Sai Aparna Aketi, Smriti Gupta, Huimei Cheng, Joycee Mekie, Peter A. Beerel
SERAD: Soft Error Resilient Asynchronous Design using a Bundled Data Protocol. CoRR (2020)
Sai Aparna Aketi, Priyadarshini Panda, Kaushik Roy
Relevant-features based Auxiliary Cells for Energy Efficient Detection of Natural Errors. CoRR (2020)
Priyadarshini Panda, Sai Aparna Aketi, Kaushik Roy
Towards Scalable, Efficient and Accurate Deep Spiking Neural Networks with Backward Residual Connections, Stochastic Softmax and Hybridization. CoRR (2019)
Sai Aparna Aketi, Joycee Mekie, Hemal Shah
Single-Error Hardened and Multiple-Error Tolerant Guarded Dual Modular Redundancy Technique. VLSI Design (2018)