activity
20212026
most citedGRADE-AO: Towards Near-Optimal Spatially-Coupled Codes With High Memories

1 citations · 1 across the 8 of their papers we have counts for

collaborators

10 papers

cs.LG2026

Stabilizing Transformer Training Through Consensus

Shyam Venkatasubramanian, Sean Moushegian, Michael Lin +3

Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various met…

cs.LG2024

Learn2Mix: Training Neural Networks Using Adaptive Data Integration

Shyam Venkatasubramanian, Vahid Tarokh

Accelerating model convergence in resource-constrained environments is essential for fast and efficient neural network training. This work presents learn2mix, a new training strate…

cs.LG2024

Steinmetz Neural Networks for Complex-Valued Data

Shyam Venkatasubramanian, Ali Pezeshki, Vahid Tarokh

We introduce a new approach to processing complex-valued data using DNNs consisting of parallel real-valued subnetworks with coupled outputs. Our proposed class of architectures, r…

cs.LG2024

RASPNet: A Benchmark Dataset for Radar Adaptive Signal Processing Applications

Shyam Venkatasubramanian, Bosung Kang, Ali Pezeshki +2

We present a large-scale dataset called RASPNet for radar adaptive signal processing (RASP) applications to support the development of data-driven models within the adaptive radar…

eess.SP2024

Data-Driven Target Localization: Benchmarking Gradient Descent Using the Cramer-Rao Bound

Shyam Venkatasubramanian, Sandeep Gogineni, Bosung Kang +1

In modern radar systems, precise target localization using azimuth and velocity estimation is paramount. Traditional unbiased estimation methods have utilized gradient descent algo…

cs.LG2023

Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks

Shyam Venkatasubramanian, Ahmed Aloui, Vahid Tarokh

Advancing loss function design is pivotal for optimizing neural network training and performance. This work introduces Random Linear Projections (RLP) loss, a novel approach that e…