Q-Exponential Processes for Heavy-Tailed Uncertainty Calibration in Deep Predictors

Authors

  • Hannah N. Martin ILR School Statistics and Data Science, Cornell University, Ithaca, New York, USA Author
  • Dylan Adams ILR School Statistics and Data Science, Cornell University, Ithaca, New York, USA Author
  • Nora Roberts ILR School Statistics and Data Science, Cornell University, Ithaca, New York, USA Author

DOI:

https://doi.org/10.66525/ijictt147

Keywords:

Uncertainty Calibration, Q-Exponential Processes, Tsallis Statistics, Deep Learning, Heavy-Tailed Distributions

Abstract

Deep predictive models have achieved unprecedented accuracy across diverse domains, yet they frequently exhibit severe overconfidence when faced with out-of-distribution data or heavy-tailed noise. Standard uncertainty calibration techniques typically rely on exponential family distributions, which inherently assume light-tailed residual behavior and fail to capture complex, long-tailed epistemic uncertainties. This paper proposes a novel framework utilizing q-exponential processes, rooted in non-extensive Tsallis statistical mechanics, to model and calibrate heavy-tailed uncertainty in deep predictors. By replacing the canonical softmax or Gaussian output layers with a generalized q-exponential formulation, we allow the network to learn the tail index of the predictive distribution dynamically. This approach provides a mathematically rigorous mechanism to bound confidence scores and decouple aleatoric from epistemic uncertainty under severe distributional shifts. Through comprehensive theoretical analysis and extensive evaluations on high-dimensional benchmarks, we demonstrate that q-exponential calibration significantly reduces Expected Calibration Error and Negative Log-Likelihood in environments characterized by extreme noise and outlier prevalence. The proposed methodology establishes a robust paradigm for reliable decision-making in safety-critical applications, offering a fundamental shift away from classical Boltzmann-Gibbs statistics in deep learning toward a more flexible, heavy-tailed geometric framework.

Downloads

Download data is not yet available.

References

1. Ross, S. A. (1976). The arbitrage theory of capital asset pricing. Journal of Economic Theory, 13(3), 341–360.

2. 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.

3. 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.

4. 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.

5. Dai, Y., Ji, Y., Zhang, X., Wang, Y., Chu, X., & Lu, Z. (2026). Harder is better: Boosting mathematical reasoning via difficulty-aware grpo and multi-aspect question reformulation. arXiv preprint arXiv:2601.20614.

6. Xu, Yuanchao, et al. "Reinforced data-driven estimation for spectral properties of Koopman semigroup in stochastic dynamical systems." arXiv preprint arXiv:2509.04265 (2025).

7. 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.

8. Li, Y., Tan, G., & Gou, C. (2024). Cascaded iterative transformer for jointly predicting facial landmark, occlusion probability and head pose. International Journal of Computer Vision, 132(4), 1242-1257.

9. 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).

10. Li, Y., Gou, C., & Tan, G. (2024). Taming uncertainty in sparse-view generalizable nerf via indirect diffusion guidance. arXiv preprint arXiv:2402.01217, 3, 2.

11. Kingma, D. P., & Welling, M. (2014). Auto-encoding variational Bayes. In Proceedings of ICLR.

12. Cakmak, S., Wang, Y., Gao, S., & Zhou, E. (2024). Contextual ranking and selection with gaussian processes and optimal computing budget allocation. ACM Transactions on Modeling and Computer Simulation, 34(2), 1-24.

13. Wang, J., Xu, Y., Li, Y., Khargonekar, P., & Faruque, M. A. A. (2026). CRUISE: Vision-Language Model-Guided Uncertainty-Aware Cross-Modal Sensor Fusion for Robust Autonomous Driving. arXiv preprint arXiv:2608.09202.

14. Cakmak, S., Zhou, E., & Gao, S. (2021, December). Contextual ranking and selection with Gaussian processes. In 2021 Winter Simulation Conference (WSC) (pp. 1-12). IEEE.

15. Acquah, C., Hoehn, S., Krul, S., Jockusch, S., Yang, S., Seth, S. K., ... & Crespo-Hernández, C. E. (2024). Electronic relaxation pathways in thio-acridone and thio-coumarin: two heavy-atom-free photosensitizers absorbing visible light. Physical Chemistry Chemical Physics, 26(46), 28980-28991.

16. 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.

17. Chang, Z., Obite, C., Zhou, S., & Lan, S. (2024). Deep Q-Exponential Processes. arXiv preprint arXiv:2410.22119.

18. 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.

19. 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).

20. Lyu, S., Mao, S., & Ma, Y. (2025). Unified Long Video Inpainting and Outpainting via Overlapping High-Order Co-Denoising. arXiv preprint arXiv:2511.03272.

21. 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.

22. Li, Q., Luo, T., Jiang, M., Liao, J., & Jiang, Z. (2024, October). Deep incomplete multi-view network semi-supervised multi-label learning with unbiased loss. In Proceedings of the 32nd ACM International Conference on Multimedia (pp. 9048-9056).

23. 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.

24. Ouyang, Z., & Mayne, P. W. (2018). Calibrating NTH method for ϕ′ in clayey soils using centrifuge CPTu. In Cone Penetration Testing 2018 (pp. 491-497). CRC Press.

25. 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).

26. Li, X., Wang, P., Li, G., & Zhang, Y. (2023). Design of a novel self-test-on-chip interface ASIC for capacitive accelerometers. IEEE Transactions on Circuits and Systems I: Regular Papers, 70(7), 2834-2843.

27. 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.

28. Zhang, J., & Tang, H. (2025). Resolving Task Objective Conflicts in Unified Model via Task-Aware Mixture-of-Experts. arXiv preprint arXiv:2506.03591.

29. Black, F., & Scholes, M. (1973). The pricing of options and corporate liabilities. Journal of Political Economy, 81(3), 637–654.

30. 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.

31. Zhang, Z., Yin, Z., Wen, J., Sun, L., Su, S., & Yu, P. S. (2021). DeepBlue: Bi-layered LSTM for tweet popularity estimation. IEEE Transactions on Knowledge and Data Engineering, 34(10), 4737-4752.

32. 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.

33. 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.

34. Yang, Y., & Zhang, S. (2024). Pixelwise calibration method for a telecentric structured light system.Applied Optics,63(10), 2562-2569.

35. Fan, J., Gao, B., Jin, H., & Jiang, L. (2022). UCC: Uncertainty guided cross-head co-training for semi-supervised semantic segmentation. In 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 9937–9946). IEEE. https://doi.org/10.1109/CVPR52688.2022.00971

Downloads

Published

2026-09-10