no code implementations • 8 Oct 2021 • Justin Gilmer, Behrooz Ghorbani, Ankush Garg, Sneha Kudugunta, Behnam Neyshabur, David Cardoze, George Dahl, Zachary Nado, Orhan Firat
In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics.
no code implementations • ICLR 2022 • Justin Gilmer, Behrooz Ghorbani, Ankush Garg, Sneha Kudugunta, Behnam Neyshabur, David Cardoze, George Edward Dahl, Zachary Nado, Orhan Firat
In this work, we study the evolution of the loss Hessian across many classification tasks in order to understand the effect the curvature of the loss has on the training dynamics.
2 code implementations • 16 Sep 2021 • Zi Wang, George E. Dahl, Kevin Swersky, Chansoo Lee, Zelda Mariet, Zachary Nado, Justin Gilmer, Jasper Snoek, Zoubin Ghahramani
Contrary to a common belief that BO is suited to optimizing black-box functions, it actually requires domain knowledge on characteristics of those functions to deploy BO successfully.
2 code implementations • 7 Jun 2021 • Zachary Nado, Neil Band, Mark Collier, Josip Djolonga, Michael W. Dusenberry, Sebastian Farquhar, Qixuan Feng, Angelos Filos, Marton Havasi, Rodolphe Jenatton, Ghassen Jerfel, Jeremiah Liu, Zelda Mariet, Jeremy Nixon, Shreyas Padhy, Jie Ren, Tim G. J. Rudner, Faris Sbahi, Yeming Wen, Florian Wenzel, Kevin Murphy, D. Sculley, Balaji Lakshminarayanan, Jasper Snoek, Yarin Gal, Dustin Tran
In this paper we introduce Uncertainty Baselines: high-quality implementations of standard and state-of-the-art deep learning methods on a variety of tasks.
no code implementations • NeurIPS 2021 • Zachary Nado, Justin M. Gilmer, Christopher J. Shallue, Rohan Anil, George E. Dahl
Recently the LARS and LAMB optimizers have been proposed for training neural networks faster using large batch sizes.
Ranked #1 on
Question Answering
on SQuAD1.1
(Hardware Burden metric)
no code implementations • 6 Nov 2020 • Alexander D'Amour, Katherine Heller, Dan Moldovan, Ben Adlam, Babak Alipanahi, Alex Beutel, Christina Chen, Jonathan Deaton, Jacob Eisenstein, Matthew D. Hoffman, Farhad Hormozdiari, Neil Houlsby, Shaobo Hou, Ghassen Jerfel, Alan Karthikesalingam, Mario Lucic, Yian Ma, Cory McLean, Diana Mincu, Akinori Mitani, Andrea Montanari, Zachary Nado, Vivek Natarajan, Christopher Nielson, Thomas F. Osborne, Rajiv Raman, Kim Ramasamy, Rory Sayres, Jessica Schrouff, Martin Seneviratne, Shannon Sequeira, Harini Suresh, Victor Veitch, Max Vladymyrov, Xuezhi Wang, Kellie Webster, Steve Yadlowsky, Taedong Yun, Xiaohua Zhai, D. Sculley
Predictors returned by underspecified pipelines are often treated as equivalent based on their training domain performance, but we show here that such predictors can behave very differently in deployment domains.
no code implementations • 10 Jul 2020 • Shreyas Padhy, Zachary Nado, Jie Ren, Jeremiah Liu, Jasper Snoek, Balaji Lakshminarayanan
Accurate estimation of predictive uncertainty in modern neural networks is critical to achieve well calibrated predictions and detect out-of-distribution (OOD) inputs.
no code implementations • 19 Jun 2020 • Zachary Nado, Shreyas Padhy, D. Sculley, Alexander D'Amour, Balaji Lakshminarayanan, Jasper Snoek
Using this one line code change, we achieve state-of-the-art on recent covariate shift benchmarks and an mCE of 60. 28\% on the challenging ImageNet-C dataset; to our knowledge, this is the best result for any model that does not incorporate additional data augmentation or modification of the training pipeline.
no code implementations • 11 Oct 2019 • Dami Choi, Christopher J. Shallue, Zachary Nado, Jaehoon Lee, Chris J. Maddison, George E. Dahl
In particular, we find that the popular adaptive gradient methods never underperform momentum or gradient descent.
1 code implementation • NeurIPS 2019 • Guodong Zhang, Lala Li, Zachary Nado, James Martens, Sushant Sachdeva, George E. Dahl, Christopher J. Shallue, Roger Grosse
Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns.
2 code implementations • NeurIPS 2019 • Yaniv Ovadia, Emily Fertig, Jie Ren, Zachary Nado, D. Sculley, Sebastian Nowozin, Joshua V. Dillon, Balaji Lakshminarayanan, Jasper Snoek
Modern machine learning methods including deep learning have achieved great success in predictive accuracy for supervised learning tasks, but may still fall short in giving useful estimates of their predictive {\em uncertainty}.
no code implementations • 16 Oct 2018 • Dan Moldovan, James M Decker, Fei Wang, Andrew A Johnson, Brian K. Lee, Zachary Nado, D. Sculley, Tiark Rompf, Alexander B. Wiltschko
In machine learning, imperative style libraries like Autograd and PyTorch are easy to write, but suffer from high interpretive overhead and are not easily deployable in production or mobile settings.