Agarwala, Atish

17 publications

ICML 2025 Avoiding Spurious Sharpness Minimization Broadens Applicability of SAM Sidak Pal Singh, Hossein Mobahi, Atish Agarwala, Yann Dauphin

ICML 2025 Exact Risk Curves of signSGD in High-Dimensions: Quantifying Preconditioning and Noise-Compression Effects Ke Liang Xiao, Noah Marshall, Atish Agarwala, Elliot Paquette

TMLR 2025 How Far Away Are Truly Hyperparameter-Free Learning Algorithms? Priya Kasimbeg, Vincent Roulet, Naman Agarwal, Sourabh Medapati, Fabian Pedregosa, Atish Agarwala, George E. Dahl

ICML 2025 Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks Shikai Qiu, Lechao Xiao, Andrew Gordon Wilson, Jeffrey Pennington, Atish Agarwala

ICLR 2025 To CLIP or Not to CLIP: The Dynamics of SGD with Gradient Clipping in High-Dimensions Noah Marshall, Ke Liang Xiao, Atish Agarwala, Elliot Paquette

TMLR 2024 Feature Learning as Alignment: A Structural Property of Gradient Descent in Non-Linear Neural Networks Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala

ICMLW 2024 Gradient Descent Induces Alignment Between Weights and the Pre-Activation Tangents for Deep Non-Linear Networks Daniel Beaglehole, Ioannis Mitliagkas, Atish Agarwala

NeurIPS 2024 Neglected Hessian Component Explains Mysteries in Sharpness Regularization Yann N. Dauphin, Atish Agarwala, Hossein Mobahi

NeurIPSW 2024 Scaling Collapse Reveals Universal Dynamics in Compute-Optimally Trained Neural Networks Shikai Qiu, Atish Agarwala, Jeffrey Pennington, Lechao Xiao

NeurIPS 2024 Stepping on the Edge: Curvature Aware Learning Rate Tuners Vincent Roulet, Atish Agarwala, Jean-Bastien Grill, Grzegorz Swirszcz, Mathieu Blondel, Fabian Pedregosa

NeurIPSW 2023 On the Interplay Between Stepsize Tuning and Progressive Sharpening Vincent Roulet, Atish Agarwala, Fabian Pedregosa

ICML 2023 SAM Operates Far from Home: Eigenvalue Regularization as a Dynamical Phenomenon Atish Agarwala, Yann Dauphin

ICML 2023 Second-Order Regression Models Exhibit Progressive Sharpening to the Edge of Stability Atish Agarwala, Fabian Pedregosa, Jeffrey Pennington

TMLR 2023 Temperature Check: Theory and Practice for Training Models with SoftMax-Cross-Entropy Losses Atish Agarwala, Samuel Stern Schoenholz, Jeffrey Pennington, Yann Dauphin

NeurIPSW 2022 A Second-Order Regression Model Shows Edge of Stability Behavior Fabian Pedregosa, Atish Agarwala, Jeffrey Pennington

ICML 2022 Deep Equilibrium Networks Are Sensitive to Initialization Statistics Atish Agarwala, Samuel S Schoenholz

ICLR 2021 One Network Fits All? Modular Versus Monolithic Task Formulations in Neural Networks Atish Agarwala, Abhimanyu Das, Brendan Juba, Rina Panigrahy, Vatsal Sharan, Xin Wang, Qiuyi Zhang