paper-with-me

홈 › Papers

Robust Calibration For Improved Weather Prediction Under Distributional Shift

2024-01-08 · Sankalp Gilda, Neel Bhandari, Wendy Mak, Andrea Panizza

In this paper, we present results on improving out-of-domain weather prediction and uncertainty estimation as part of the \texttt{Shifts Challenge on Robustness and Uncertainty under Real-World Distributional Shift} challenge. We find that by leveraging a mixture of experts in conjunction with an advanced data augmentation technique borrowed from the computer vision domain, in conjunction with robust \textit{post-hoc} calibration of predictive uncertainties, we can potentially achieve more accurate and better-calibrated results with deep neural networks than with boosted tree models for tabular data. We quantify our predictions using several metrics and propose several future lines of inquiry and experimentation to boost performance.

📄 PDF Abstract BibTeX arXiv:2401.04144

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationMixture-of-ExpertsPrediction

Similar Papers 제목 키워드 기반

Recipes for Calibration Checks in Safety-Critical Applications

2026-04-29 · Romeo Valentin arxiv

Safety-critical prediction systems, such as autonomous vehicles, weather forecasters, and medical monitors, commonly rely on probabilistic forecasters. These forecasters make predictions about possible future outcomes, a…

Robot Pose EstimationAutonomous VehiclesWeather ForecastingDecision Making

Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction

2026-06-17 · Anna Asch, Raphael Rossellini, Pedram Hassanzadeh, Rebecca Willett arxiv

Probabilistic weather forecasting is undergoing rapid transformation with artificial intelligence (AI). In traditional numerical weather prediction, computing power can limit how well ensemble forecasts approximate the u…

Weather Forecasting

Machine learning-based probabilistic forecasting of solar irradiance in Chile

2024-11-17 · Sándor Baran, Julio C. Marín, Omar Cuevas, Mailiu Díaz 외

By the end of 2023, renewable sources cover 63.4% of the total electric power demand of Chile, and in line with the global trend, photovoltaic (PV) power shows the most dynamic increase. Although Chile's Atacama Desert i…

Weather Forecasting

Improving Calibration through the Relationship with Adversarial Robustness

2020-06-29 · NeurIPS 2021 12 · Yao Qin, Xuezhi Wang, Alex Beutel, Ed H. Chi

Neural networks lack adversarial robustness, i.e., they are vulnerable to adversarial examples that through small perturbations to inputs cause incorrect predictions. Further, trust is undermined when models give miscali…

Adversarial Robustness

Improving model calibration with accuracy versus uncertainty optimization

2020-12-14 · NeurIPS 2020 12 · Ranganath Krishnan, Omesh Tickoo

Obtaining reliable and accurate quantification of uncertainty estimates from deep neural networks is important in safety-critical applications. A well-calibrated model should be accurate when it is certain about its pred…

image-classificationImage ClassificationmodelVariational Inference