Neural variational inference for cutting feedback during uncertainty propagation

2025-10-11

AI Summary

In scientific analysis, propagating upstream estimation uncertainty to downstream Bayesian inference—while rigorously severing feedback loops—is essential yet challenging. Existing cut-Bayes methods either rely on nested MCMC or require access to upstream data and model specifications, rendering them computationally expensive and deployment-limited. We propose NeVI-Cut: a modular neural variational inference framework that operates solely on upstream posterior samples, without requiring upstream data or model architecture. NeVI-Cut innovatively integrates conditional normalizing flows with Monte Carlo-averaged loss, circumventing explicit variational approximation of the upstream model. Crucially, we establish, for the first time, a theoretical guarantee of consistent KL-divergence approximation for conditional normalizing flows. Experiments demonstrate that NeVI-Cut significantly outperforms state-of-the-art cut-Bayes methods in both accuracy and computational efficiency.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Inference
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

In many scientific applications, uncertainty of estimates from an earlier (upstream) analysis needs to be propagated in subsequent (downstream) Bayesian analysis, without feedback. Cutting feedback methods, also termed cut-Bayes, achieve this by constructing a cut-posterior distribution that prevents backward information flow. Cutting feedback like nested MCMC is computationally challenging while variational inference (VI) cut-Bayes methods need two variational approximations and require access to the upstream data and model. In this manuscript we propose, NeVI-Cut, a provably accurate and modular neural network-based variational inference method for cutting feedback. We directly utilize samples from the upstream analysis without requiring access to the upstream data or model. This simultaneously preserves modularity of analysis and reduces approximation errors by avoiding a variational approximation for the upstream model. We then use normalizing flows to specify the conditional variational family for the downstream parameters and estimate the conditional cut-posterior as a variational solution of Monte Carlo average loss over all the upstream samples. We provide theoretical guarantees on the NeVI-Cut estimate to approximate any cut-posterior. Our results are in a fixed-data regime and provide convergence rates of the actual variational solution, quantifying how richness of the neural architecture and the complexity of the target cut-posterior dictate the approximation quality. In the process, we establish new results on uniform Kullback-Leibler approximation rates of conditional normalizing flows. Simulation studies and two real-world analyses illustrate how NeVI-Cut achieves significant computational gains over traditional cutting feedback methods and is considerably more accurate than parametric variational cut approaches.

Problem

• Propagating upstream uncertainty without feedback in Bayesian analysis
• Overcoming computational challenges of existing cut-Bayes methods
• Developing neural variational inference without upstream data access

Innovation

• Neural variational inference for cutting feedback
• Uses upstream samples without upstream data
• Normalizing flows approximate conditional cut-posterior