activity
20222026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2025

Controllable Probabilistic Forecasting with Stochastic Decomposition Layers

John S. Schreck, William E. Chapman, Charlie Becker +6

AI weather prediction ensembles with latent noise injection and optimized with the continuous ranked probability score (CRPS) have produced both accurate and well-calibrated predic…

cs.LG2025

Consistency Conditions for Differentiable Surrogate Losses

Drona Khurana, Anish Thilagar, Dhamma Kimpara +1

The statistical consistency of surrogate losses for discrete prediction tasks is often checked via the condition of calibration. However, directly verifying calibration can be ardu…

cs.LG2024

Trading off Consistency and Dimensionality of Convex Surrogates for the Mode

Enrique Nueve, Bo Waggoner, Dhamma Kimpara +1

In multiclass classification over outcomes, the outcomes must be embedded into the reals with dimension at least in order to design a consistent surrogate loss that leads…

cs.LG2023

Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applications

John S. Schreck, David John Gagne, Charlie Becker +13

Robust quantification of predictive uncertainty is critical for understanding factors that drive weather and climate outcomes. Ensembles provide predictive uncertainty estimates an…

cs.LG2022

Proper losses for discrete generative models

Rafael Frongillo, Dhamma Kimpara, Bo Waggoner

We initiate the study of proper losses for evaluating generative models in the discrete setting. Unlike traditional proper losses, we treat both the generative model and the target…