mlsanityData to 7 Oct 2026

Robust Calibration For Improved Weather Prediction Under Distributional Shift

arXiv 2401.04144 ↗First posted 8 Jan 2024cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we present results on improving out-of-domain weather prediction and uncertainty estimation as part of the textttShifts 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 textitpost-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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 47 references that are in the map. First posted on arXiv 8 Jan 2024.

Builds on

21 of 47 references.

References · 21

  1. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  2. 2019Invariant Risk Minimizationcited by 1,832
  3. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  4. 2021Revisiting Deep Learning Models for Tabular Datacited by 725
  5. 2019Large Batch Optimization for Deep Learning: Training BERT in 76 minutescited by 671
  6. 2015Cyclical Learning Rates for Training Neural Networkscited by 627
  7. 2021On Calibration and Out-of-domain Generalizationcited by 134
  8. 2019NGBoost: Natural Gradient Boosting for Probabilistic Predictioncited by 94
  9. 2020Gradient Centralization: A New Optimization Technique for Deep Neural Networkscited by 82
  10. 2020On Feature Normalization and Data Augmentationcited by 71
  11. 2021Uncertainty Toolbox: an Open-Source Library for Assessing, Visualizing, and Improving Uncertainty Quantificationcited by 57
  12. 2019Positional Normalizationcited by 28
9 more
  1. 2015The Use of Machine Learning Algorithms in Recommender Systems: A Systematic Reviewcited by 27
  2. 2017Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modelingcited by 25
  3. 2021Multivariate Deep Evidential Regressioncited by 23
  4. 2021Simple Modifications to Improve Tabular Neural Networkscited by 14
  5. 2021Unsupervised Domain Adaptation for Constraining Star Formation Historiescited by 8
  6. 2021Uncertainty-Aware Learning for Improvements in Image Quality of the Canada-France-Hawaii Telescopecited by 6
  7. 2019Feature Selection for Better Spectral Characterization or: How I Learned to Start Worrying and Love Ensemblescited by 2
  8. 2023deep-REMAP: Parameterization of Stellar Spectra Using Regularized Multi-Task Learningcited by 2
  9. 2023Beyond mirkwood: Enhancing SED Modeling with Conformal Predictionscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024CoDiCast: Conditional Diffusion Model for Global Weather Prediction with Uncertainty Quantification
  2. 2026Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting
  3. 2025Rectifying Distribution Shift in Cascaded Precipitation Nowcasting
  4. 2026Universal Diffusion-Based Probabilistic Downscaling
  5. 2026Proper Scoring Rule-based Diffusion for Probabilistic Weather Forecasting
  6. 2026AdaWeather: Adaptively Mixing Probabilistic Weather Forecasts with Logarithmic Regret
  7. 2023PreDiff: Precipitation Nowcasting with Latent Diffusion Models
  8. 2026Stress-Testing Dynamical and Generative Downscaling Using Subseasonal Extreme Precipitation Forecasts