Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Ma, Zhenyao, Liang, Yue, Li, Dongxu
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910030366769152
author Ma, Zhenyao
Liang, Yue
Li, Dongxu
author_facet Ma, Zhenyao
Liang, Yue
Li, Dongxu
contents Inspired by behavioral science, we propose Behavior Learning (BL), a novel general-purpose machine learning framework that learns interpretable and identifiable optimization structures from data, ranging from single optimization problems to hierarchical compositions. It unifies predictive performance, intrinsic interpretability, and identifiability, with broad applicability to scientific domains involving optimization. BL parameterizes a compositional utility function built from intrinsically interpretable modular blocks, which induces a data distribution for prediction and generation. Each block represents and can be written in symbolic form as a utility maximization problem (UMP), a foundational paradigm in behavioral science and a universal framework of optimization. BL supports architectures ranging from a single UMP to hierarchical compositions, the latter modeling hierarchical optimization structures. Its smooth and monotone variant (IBL) guarantees identifiability. Theoretically, we establish the universal approximation property of BL, and analyze the M-estimation properties of IBL. Empirically, BL demonstrates strong predictive performance, intrinsic interpretability and scalability to high-dimensional data. Code: https://github.com/MoonYLiang/Behavior-Learning ; install via pip install blnetwork.
format Preprint
id arxiv_https___arxiv_org_abs_2602_20152
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data
Ma, Zhenyao
Liang, Yue
Li, Dongxu
Machine Learning
Artificial Intelligence
I.2.6
Inspired by behavioral science, we propose Behavior Learning (BL), a novel general-purpose machine learning framework that learns interpretable and identifiable optimization structures from data, ranging from single optimization problems to hierarchical compositions. It unifies predictive performance, intrinsic interpretability, and identifiability, with broad applicability to scientific domains involving optimization. BL parameterizes a compositional utility function built from intrinsically interpretable modular blocks, which induces a data distribution for prediction and generation. Each block represents and can be written in symbolic form as a utility maximization problem (UMP), a foundational paradigm in behavioral science and a universal framework of optimization. BL supports architectures ranging from a single UMP to hierarchical compositions, the latter modeling hierarchical optimization structures. Its smooth and monotone variant (IBL) guarantees identifiability. Theoretically, we establish the universal approximation property of BL, and analyze the M-estimation properties of IBL. Empirically, BL demonstrates strong predictive performance, intrinsic interpretability and scalability to high-dimensional data. Code: https://github.com/MoonYLiang/Behavior-Learning ; install via pip install blnetwork.
title Behavior Learning (BL): Learning Hierarchical Optimization Structures from Data
topic Machine Learning
Artificial Intelligence
I.2.6
url https://arxiv.org/abs/2602.20152