Vol. 1 No. 4 (2026)

Articles

Bayesian Latent Priors for Calibrated Uncertainty During Deployment-Time Representation Shifts

Published 2026-10-17

  • Brandon Hall
    • ,
  • Michael Martinez
    • ,
  • Aiden Reyes

Brandon Hall
Department of Software Engineering, Golisano College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, New York, 14623, USA

Michael Martinez
Paul G. Allen School of Computer Science & Engineering, University of Washington, Seattle, Washington, USA

Aiden Reyes
Department of Software Engineering, Golisano College of Computing and Information Sciences, Rochester Institute of Technology, Rochester, New York, 14623, USA

Data Science and Computational Intelligence, Volume 1, Issue 4, 2026 cover

Abstract

The deployment of deep neural networks in high-stakes environments is frequently compromised by representation shifts, where the distribution of data encountered during inference diverges significantly from the training distribution. Under such conditions, standard deterministic models exhibit severe overconfidence, leading to poorly calibrated uncertainty estimates that can result in catastrophic downstream failures. While Bayesian Neural Networks offer a principled framework for uncertainty quantification, traditional isotropic Gaussian priors in parameter space often fail to translate into meaningful uncertainty bounds in the functional or latent representation spaces, particularly when extrapolation is required. This paper introduces a novel framework utilizing Bayesian latent priors designed specifically to maintain calibrated uncertainty during deployment-time representation shifts. By modeling the prior distribution directly within the latent manifold rather than the parameter space, the proposed method adapts to shifts in the underlying data generating process. We present a comprehensive theoretical foundation for representation shifts and derive a modified Evidence Lower Bound that incorporates a density ratio estimator to dynamically adjust the latent prior. Extensive analysis demonstrates that our approach significantly improves uncertainty calibration metrics, such as Expected Calibration Error, across varying degrees of domain shift. The findings underscore the critical importance of representation-level prior specification for robust probabilistic inference, offering a scalable solution for deploying machine learning models in dynamic, real-world environments.

Keywords

Bayesian Inference, Uncertainty Calibration, Representation Shift, Latent Manifold, Out-of-Distribution Detection

PDF

Author Biography

Brandon Hall

Editorial correspondence on behalf of the authors

References

  1. Lyu, S., Mao, S., & Ma, Y. (2025). Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising. arXiv preprint arXiv:2511.03272.
  2. Zhang, J., Luo, H., Yang, H., Xu, X., Wu, Q., Shi, Y., ... & Wang, J. (2023). Neuraldome: A neural modeling pipeline on multi-view human-object interactions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 8834-8845).
  3. Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., et al. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv preprint arXiv:1711.05225.
  4. Gao, S., Du, J., & Chen, C. H. (2019, August). Selecting the optimal system design under covariates. In 2019 ieee 15th international conference on automation science and engineering (case) (pp. 547-552). IEEE.
  5. Huang, Y., Roth, K., Bouniot, Q., Xu, W., & Akata, Z. (2026). Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers. arXiv preprint arXiv:2601.20796.
  6. Li, Q., Xu, T., Luo, T., Zhong, Y., Li, Y., Zhou, Y., & Hou, C. (2026). Theory-driven label-specific representation for incomplete multi-view multi-label learning. Advances in Neural Information Processing Systems, 38, 121996-122037.
  7. Chen, Y., Xiang, F., Hernandez, M. L., Carpenter, D., Bozkurt, A., & Lobaton, E. (2025). Robust multimodal cough detection with optimized out-of-distribution detection for wearables. IEEE Journal of Biomedical and Health Informatics.
  8. Zhang, F., Gao, S., & Song, J. (2024, August). Offline Contextual Learning with Correlated Bayesian Beliefs. In 2024 IEEE 20th International Conference on Automation Science and Engineering (CASE) (pp. 2496-2500). IEEE.
  9. He, H., Sun, Z., Fan, J., & Mok, P. Y. (2025). TiPGAN: High-quality tileable textures synthesis with intrinsic priors for cloth digitization applications. Computer-Aided Design, 183, 103866.
  10. Hu, H., Yang, Y., Zhao, Q., & Zhang, C. (2022, June). On the role of discount factor in offline reinforcement learning. In International conference on machine learning (pp. 9072-9098). PMLR.
  11. Kermany, D. S., Goldbaum, M., Cai, W., Valentim, C. C. S., Liang, H., Baxter, S. L., et al. (2018). Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell, 172(5), 1122–1131.
  12. Yao, Z., Hawi, P., Aitharaju, V., Mahishi, J., & Ghanem, R. (2026). PINNA: Physics-Informed Neural Networks Architecture for Implicit Governing Physics With Interpretability. International Journal for Numerical Methods in Engineering, 127(17), e70399.
  13. Chang, Z., Obite, C., Zhou, S., & Lan, S. (2024). Deep Q-Exponential Processes. arXiv preprint arXiv:2410.22119.
  14. Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115–118.
  15. Pei, Z., Huang, Q., & Wang, S. (2025). Neuronal Group Communication for Efficient Neural representation. arXiv preprint arXiv:2510.16851.
  16. Qu, W., Shao, Y., Meng, L., Huang, X., & Xiao, L. (2024, June). A conditional denoising diffusion probabilistic model for point cloud upsampling. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 20786-20795). IEEE.
  17. Li, H., Wang, Y., Huang, T., Huang, H., Wang, H., & Chu, X. (2025, October). Ld-rps: Zero-shot unified image restoration via latent diffusion recurrent posterior sampling. In 2025 IEEE/CVF International Conference on Computer Vision (ICCV) (pp. 13684-13694). IEEE.
  18. Wu, J., Chen, S., Heo, I., Gutfraind, S., Liu, S., Li, C., ... & Sharps, M. (2025). Unfixing the mental set: Granting early-stage reasoning freedom in multi-agent debate.
  19. Sun, L., Hu, J., Li, M., & Peng, H. (2024, July). R-ode: Ricci curvature tells when you will be informed. In Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (pp. 2594-2598).
  20. Zhang, S., Zhang, E., Cookson, J., Huang, P., & Yan, W. (2026). Semi-Analytical Prediction of Attainable Lateral Capacity for Hybrid Suction Caissons Considering Soil-Plug Heave and Piping during Installation in Sand. Ocean Engineering.
  21. Zhang, Y., Pleus, A., & Althoff, M. (2026, July). Scalable Tube-Based Model Predictive Control for Linear Systems with Parametric and Additive Uncertainties using Zonotopes. In 2026 European Control Conference (ECC) (pp. 509-516). IEEE.
  22. Sang, Y. (2026, March). Adaptive Quantization Strategies for Robust ML Inference Under Distribution Shift. In Proceedings of the 2026 5th International Conference on Cyber Security, Artificial Intelligence and Digital Economy (pp. 362-368).
  23. Li, X., Wang, P., Li, G., Ni, L., & Zhang, Y. (2023). Design of interface circuits and lightweight PUF for TMR sensors. IEEE Sensors Journal, 23(11), 11754-11761.
  24. Chen, L., Wang, J., Mortlock, T., Khargonekar, P., & Al Faruque, M. A. (2025, June). Hyperdimensional uncertainty quantification for multimodal uncertainty fusion in autonomous vehicles perception. In 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 22306-22316). IEEE.
  25. Qiao, Z., Yang, R., Lyu, J., Li, X., Dai, Z., Yang, Z., ... & Qiu, S. (2026, April). Dual-robust cross-domain offline reinforcement learning against dynamics shifts. In International Conference on Learning Representations (Vol. 2026, pp. 69596-69634).
  26. Li, Y. (2026, June). AI-augmented automated triage for system error reporting using log and memory dump analysis. In 2026 7th International Conference on Big Data & Artificial Intelligence & Software Engineering (ICBASE) (pp. 572-577). IEEE.
  27. Obite, C. P., Chang, Z., Wu, K., & Lan, S. (2025, May). Bayesian regularization of latent representation. In International Conference on Learning Representations (Vol. 2025, pp. 12805-12823).
  28. Chai, L.; Zhang, J.; Li, H.; Cui, C.; Jiang, J.; Zheng, B.; Wu, L.; Jiang, L. Investigation of thermomorphogenesis-related genes for a multi-silique trait in Brassica napus by comparative transcriptome analysis. Front. Genet. 2021, 12, 678804.
  29. Sha, L., Wang, Y., Meng, P., Deng, Y., Chen, T., Zhang, X., ... & Xu, Q. (2025). Pharmacological inhibition of PSPH reduces serine levels and epileptic seizures. Nature Chemical Biology, 21(11), 1742-1753.
  30. Mo Z. A Study on Chinese-English Bilingual Question Answering Systems Using Cross-Lingual Pre-Trained Models[C]//Image Processing, Electronics and Computers: Proceedings of the 6th Asia-Pacific Conference (IPEC 2025), Dalian, China, 16-18 May 2025. 1 Oliver's Yard, 55 City Road, London, EC1Y 1SP: SAGE Publications, 2025: 1715-1724.
  31. Zhao, J., Zhang, C., Qin, M., & Yang, P. (2025). QuantFactor REINFORCE: mining steady formulaic alpha factors with variance-bounded REINFORCE. IEEE Transactions on Signal Processing, 73, 2448-2463.
  32. Li, Q., Liu, Z., Xu, T., Luo, T., & Hou, C. (2026). Adaptive Disentangled Representation Learning for Incomplete Multi-View Multi-Label Classification. arXiv preprint arXiv:2601.05785.