33 citations · 76 across the 16 of their papers we have counts for
17 papers
Canaries in the Bank: Auditing User-Level Privacy in Private Evolution
Sai Aparna Aketi, Enayat Ullah, Shripad Gade
Private Evolution (PE) generates high-fidelity synthetic data in federated settings without exposing users' raw data. It aggregates clipped user votes over a shared candidate bank…
Efficient DP-SGD for LLMs with Randomized Clipping
Enayat Ullah, Sai Aparna Aketi, Devansh Gupta +2
Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, pr…
SADDLe: Sharpness-Aware Decentralized Deep Learning with Heterogeneous Data
Sakshi Choudhary, Sai Aparna Aketi, Kaushik Roy
Decentralized training enables learning with distributed datasets generated at different locations without relying on a central server. In realistic scenarios, the data distributio…
Towards Two-Stream Foveation-based Active Vision Learning
Timur Ibrayev, Amitangshu Mukherjee, Sai Aparna Aketi +1
Deep neural network (DNN) based machine perception frameworks process the entire input in a one-shot manner to provide answers to both "what object is being observed" and "where it…
AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression
Sai Aparna Aketi, Abolfazl Hashemi, Kaushik Roy
Decentralized learning is crucial in supporting on-device learning over large distributed datasets, eliminating the need for a central server. However, the communication overhead r…
Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data
Sai Aparna Aketi, Sakshi Choudhary, Kaushik Roy
State-of-the-art decentralized learning algorithms typically require the data distribution to be Independent and Identically Distributed (IID). However, in practical scenarios, the…
Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data
Sai Aparna Aketi, Kaushik Roy
The current state-of-the-art decentralized learning algorithms mostly assume the data distribution to be Independent and Identically Distributed (IID). However, in practical scenar…
Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data
Sai Aparna Aketi, Abolfazl Hashemi, Kaushik Roy
Decentralized learning enables the training of deep learning models over large distributed datasets generated at different locations, without the need for a central server. However…
Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning
Deepak Ravikumar, Gobinda Saha, Sai Aparna Aketi +1
Decentralized learning enables serverless training of deep neural networks (DNNs) in a distributed manner on multiple nodes. This allows for the use of large datasets, as well as t…
CoDeC: Communication-Efficient Decentralized Continual Learning
Sakshi Choudhary, Sai Aparna Aketi, Gobinda Saha +1
Training at the edge utilizes continuously evolving data generated at different locations. Privacy concerns prohibit the co-location of this spatially as well as temporally distrib…
Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data Distributions
Sai Aparna Aketi, Sangamesh Kodge, Kaushik Roy
Decentralized learning over distributed datasets can have significantly different data distributions across the agents. The current state-of-the-art decentralized algorithms mostly…
Low Precision Decentralized Distributed Training over IID and non-IID Data
Sai Aparna Aketi, Sangamesh Kodge, Kaushik Roy
Decentralized distributed learning is the key to enabling large-scale machine learning (training) on edge devices utilizing private user-generated local data, without relying on th…
Sparse-Push: Communication- & Energy-Efficient Decentralized Distributed Learning over Directed & Time-Varying Graphs with non-IID Datasets
Sai Aparna Aketi, Amandeep Singh, Jan Rabaey
Current deep learning (DL) systems rely on a centralized computing paradigm which limits the amount of available training data, increases system latency, and adds privacy and secur…
Relevant-features based Auxiliary Cells for Energy Efficient Detection of Natural Errors
Sai Aparna Aketi, Priyadarshini Panda, Kaushik Roy
Deep neural networks have demonstrated state-of-the-art performance on many classification tasks. However, they have no inherent capability to recognize when their predictions are…
Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks
Sai Aparna Aketi, Sourjya Roy, Anand Raghunathan +1
The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. Howev…
SERAD: Soft Error Resilient Asynchronous Design using a Bundled Data Protocol
Sai Aparna Aketi, Smriti Gupta, Huimei Cheng +2
The risk of soft errors due to radiation continues to be a significant challenge for engineers trying to build systems that can handle harsh environments. Building systems that are…
Towards Scalable, Efficient and Accurate Deep Spiking Neural Networks with Backward Residual Connections, Stochastic Softmax and Hybridization
Priyadarshini Panda, Aparna Aketi, Kaushik Roy
Spiking Neural Networks (SNNs) may offer an energy-efficient alternative for implementing deep learning applications. In recent years, there have been several proposals focused on…