Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
This work proposes an alternative to Bayesian NNs that is simple to implement, readily parallelizable, requires very little hyperparameter tuning, and yields high quality predictive uncertainty estimates.
AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
- Dan Hendrycks, Norman Mu, E. D. Cubuk, Barret Zoph, J. Gilmer, Balaji Lakshminarayanan
- Computer ScienceICLR
- 5 December 2019
AugMix significantly improves robustness and uncertainty measures on challenging image classification benchmarks, closing the gap between previous methods and the best possible performance in some cases by more than half.
Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
A large-scale benchmark of existing state-of-the-art methods on classification problems and the effect of dataset shift on accuracy and calibration is presented, finding that traditional post-hoc calibration does indeed fall short, as do several other previous methods.
Do Deep Generative Models Know What They Don't Know?
- Eric T. Nalisnick, Akihiro Matsukawa, Y. Teh, Dilan Görür, Balaji Lakshminarayanan
- Computer ScienceICLR
- 27 September 2018
The density learned by flow-based models, VAEs, and PixelCNNs cannot distinguish images of common objects such as dogs, trucks, and horses from those of house numbers, and such behavior persists even when the flows are restricted to constant-volume transformations.
Normalizing Flows for Probabilistic Modeling and Inference
- G. Papamakarios, Eric T. Nalisnick, Danilo Jimenez Rezende, S. Mohamed, Balaji Lakshminarayanan
- Computer ScienceJ. Mach. Learn. Res.
- 5 December 2019
This review places special emphasis on the fundamental principles of flow design, and discusses foundational topics such as expressive power and computational trade-offs, and summarizes the use of flows for tasks such as generative modeling, approximate inference, and supervised learning.
The Cramer Distance as a Solution to Biased Wasserstein Gradients
This paper describes three natural properties of probability divergences that it believes reflect requirements from machine learning: sum invariance, scale sensitivity, and unbiased sample gradients and proposes an alternative to the Wasserstein metric, the Cramer distance, which possesses all three desired properties.
Likelihood Ratios for Out-of-Distribution Detection
This work investigates deep generative model based approaches for OOD detection and observes that the likelihood score is heavily affected by population level background statistics, and proposes a likelihood ratio method forDeep generative models which effectively corrects for these confounding background statistics.
Mondrian Forests: Efficient Online Random Forests
Mondrian forests achieve competitive predictive performance comparable with existing online random forests and periodically retrained batch random forests, while being more than an order of magnitude faster, thus representing a better computation vs accuracy tradeoff.
Deep Ensembles: A Loss Landscape Perspective
Developing the concept of the diversity--accuracy plane, it is shown that the decorrelation power of random initializations is unmatched by popular subspace sampling methods and the experimental results validate the hypothesis that deep ensembles work well under dataset shift.
Variational Approaches for Auto-Encoding Generative Adversarial Networks
- Mihaela Rosca, Balaji Lakshminarayanan, David Warde-Farley, S. Mohamed
- Computer ScienceArXiv
- 15 June 2017
This paper develops a principle upon which auto-encoders can be combined with generative adversarial networks by exploiting the hierarchical structure of the generative model, and describes a unified objective for optimization.