13 citations · 35 across the 8 of their papers we have counts for
9 papers
Personalized Projected Ascent for Federated Stackelberg Optimization
M Yashwanth, Sharannya Ghosh, Saikiran Bulusu +1
Federated minimax problems, such as distributionally robust optimization and adversarial training, include an inner maximization variable built from each client's local data. These…
Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participation
M Yashwanth, Arunabh Singh, Ashok Nayak +2
Federated Learning (FL) algorithms implicitly assume that clients passively comply with server-side orchestration by sharing local model updates upon server request. However, this…
Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
Daouda Sow, Herbert Woisetschläger, Saikiran Bulusu +3
Pretraining large language models (LLMs) on vast and heterogeneous datasets is crucial for achieving state-of-the-art performance across diverse downstream tasks. However, current…
On Distributed and Asynchronous Sampling of Gaussian Processes for Sequential Binary Hypothesis Testing
Nandan Sriranga, Saikiran Bulusu, Baocheng Geng +1
In this work, we consider a binary sequential hypothesis testing problem with distributed and asynchronous measurements. The aim is to analyze the effect of sampling times of joint…
Ordered Transmission-based Detection in Distributed Networks in the Presence of Byzantines
Chen Quan, Saikiran Bulusu, Baocheng Geng +1
The ordered transmission (OT) scheme reduces the number of transmissions needed in the network to make the final decision, while it maintains the same probability of error as the s…
Distributed Stochastic Non-Convex Optimization: Momentum-Based Variance Reduction
Prashant Khanduri, Pranay Sharma, Swatantra Kafle +3
In this work, we propose a distributed algorithm for stochastic non-convex optimization. We consider a worker-server architecture where a set of worker nodes (WNs) in collabora…
Anomalous Example Detection in Deep Learning: A Survey
Saikiran Bulusu, Bhavya Kailkhura, Bo Li +2
Deep Learning (DL) is vulnerable to out-of-distribution and adversarial examples resulting in incorrect outputs. To make DL more robust, several posthoc (or runtime) anomaly detect…
Byzantine Resilient Non-Convex SVRG with Distributed Batch Gradient Computations
Prashant Khanduri, Saikiran Bulusu, Pranay Sharma +1
In this work, we consider the distributed stochastic optimization problem of minimizing a non-convex function in an adversarial sett…
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…