cs.LGMay 16, 2025

Bidirectional Information Flow (BIF) - A Sample Efficient Hierarchical Gaussian Process for Bayesian Optimization

Authors: Juan D. Guerra, Thomas Garbay, Numa Dancause, Guillaume Lajoie, Marco Bonizzato

Organizations: Polytechnique Montréal Department of Computer and Software Engineering · Mila - Québec Artificial Intelligence Institute · Polytechnique Montréal Department of Electrical Engineering · Université de Montréal Department of Neuroscience · 

Abstract

Hierarchical Gaussian Process (H-GP) models divide problems into different subtasks, allowing for different components to address each part, making them well-suited for problems with inherent compositional structure. However, existing H-GP frameworks typically employ one-way information sharing - either top-down or bottom-up - which limits sample efficiency and slows convergence. We propose Bidirectional Information Flow (BIF), which establishes continuous two-way communication. BIF retains the modular structure of hierarchical models - the parent conditions its own posterior on child summaries, treating them as structured priors - while introducing top-down feedback to softly decompose environment observations from the parent into sub-responses. This mutual exchange improves sample efficiency, enables robust training, and allows modular reuse of learned subtask models. We prove analytically the regret of a GP with a learned kernel scales linearly with the mismatch to the true kernel, tightening in the hierarchical case to the sum of child-level errors. Ablation shows removing the downward pathway collapses child R2R^2 by up to 58%. Across synthetic, neurostimulation, and HPO benchmarks, BIF achieves up to 4×4\times higher parent R2R^2 and roughly 100% AUC improvement over vanilla GPBO, and outperforms or is the runner-up in 38/40 tests compared to the state-of-the-art baselines while supporting modular child transfer to novel composite tasks.

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Hierarchy-GBP: Accelerating Factor Graph Inference via Abstraction and Recovery

    Oct 4, 2026Yuzhou Cheng, Tom Yates, Ignacio Alzugaray +3Gaussian Belief PropagationBelief Propagation

  2. Hierarchical Cooperative GFlowNets

    Oct 25, 2026Pedro Dall'Antonia, Juan Belieni, Ana Carolina Erthal +3Generative Flow NetworksDiversity-Aware Sampling

  3. Online Adaptive Kernel Mixing for Gaussian Process Decision Making

    Sep 17, 2026Kavin Aravindan, Mani Tej Sriram, Gautam Dasarathy +1Bayesian OptimizationOnline Learning with Expert Advice