(* denotes equal contribution) Implicit Bias and Convergence Rates for Self-attention Bhavya Vasudeva*, Puneesh Deora*, and Christos Thrampoulidis. Preprint. On the Optimization and Generalization of Multi-head Attention Puneesh Deora*, Rouzbeh Ghaderi*, Hossein Taheri*, and Christos Thrampoulidis. TMLR 2024, and HiLD at ICML 2023. Fast Test Error Rates for Gradient-based Algorithms on Separable Data Puneesh Deora*, Bhavya Vasudeva*, Vatsal Sharan, Christos Thrampoulidis. HiLD at ICML 2023, and ICASSP 2024. On Weighted Cross-Entropy for Label-Imbalanced Separable Data: An Algorithmic-Stability Study Puneesh Deora, and Christos Thrampoulidis. ICASSP 2023. Compressed Sensing MRI Reconstruction with Co-VeGAN: Complex-Valued Generative Adversarial Network Bhavya Vasudeva*, Puneesh Deora*, Saumik Bhattacharya, and P.M. Pradhan. WACV 2022. LoOp: Looking for Optimal Hard Negative Embeddings for Deep Metric Learning Bhavya Vasudeva*, Puneesh Deora*, Saumik Bhattacharya, Umapada Pal, and Sukalpa Chanda. ICCV 2021. Structure Preserving Compressive Sensing MRI Reconstruction using Generative Adversarial Networks Puneesh Deora*, Bhavya Vasudeva*, Saumik Bhattacharya, and P.M. Pradhan. CVPR Workshops 2020.