When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees

Title:When Has a Bayesian Neural Network Sampled Enough? Adaptive Inference Time with Statistical Guarantees

Abstract:Bayesian neural network predictions are commonly approximated using a fixed number of Monte Carlo samples per input, without controlling the resulting error that comes from this finite sample. We propose the use of confidence sequences to dynamically determine how many samples are needed while maintaining statistical guarantees. We consider several ways in which predictive probabilities are used, including identifying the most likely class, approximating the full predictive distribution, and resolving probability-threshold decisions. Sampling stops once the corresponding decision can be made with the desired guarantee. Experiments show that the method allocates the computational budget efficiently, assigning more samples to ambiguous inputs than to easy inputs while preserving reliable decisions and reducing overall latency relative to a fixed Monte Carlo budget.

40th Conference on Neural Information Processing Systems (NeurIPS 2026). Workshop: E-Values: From Statistics to ML

Artificial Intelligence (cs.AI)

arXiv:2610.12212 [cs.AI]

(or arXiv:2610.12212v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2610.12212 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.