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