Kalra, Dayal Singh

6 publications

ICML 2025 (How) Can Transformers Predict Pseudo-Random Numbers? Tao Tao, Darshil Doshi, Dayal Singh Kalra, Tianyu He, Maissam Barkeshli

ICLR 2025 Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos Dayal Singh Kalra, Tianyu He, Maissam Barkeshli

NeurIPSW 2024 On Your Mark, Get Set, Warmup! Dayal Singh Kalra, Maissam Barkeshli

NeurIPSW 2024 Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos Dayal Singh Kalra, Tianyu He, Maissam Barkeshli

NeurIPS 2024 Why Warmup the Learning Rate? Underlying Mechanisms and Improvements Dayal Singh Kalra, Maissam Barkeshli

NeurIPS 2023 Phase Diagram of Early Training Dynamics in Deep Neural Networks: Effect of the Learning Rate, Depth, and Width Dayal Singh Kalra, Maissam Barkeshli