Search Results for author:
Found 4 papers, 2 papers with code
Frustratingly Easy Uncertainty Estimation for Distribution Shift
While the primary goal is to improve accuracy under distribution shift, an important secondary goal is uncertainty estimation: evaluating the probability that the prediction of a model is correct.
Uncertainty for deep image classifiers on out of distribution data.
In addition to achieving high accuracy, in many applications, it is important to estimate the probability that a model prediction is correct.
No-collision Transportation Maps
Transportation maps between probability measures are critical objects in numerous areas of mathematics and applications such as PDE, fluid mechanics, geometry, machine learning, computer science, and economics.
Optimization and Control 49M27,
Calibrated Top-1 Uncertainty estimates for classification by score based models
While the accuracy of modern deep learning models has significantly improved in recent years, the ability of these models to generate uncertainty estimates has not progressed to the same degree.
