Saved in:
Bibliographic Details
Main Authors: Zhang, Haoran, Cha, Seohyeon, Beytur, Hasan Burhan, Chan, Kevin S, de Veciana, Gustavo, Vikalo, Haris
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.04247
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910041063292928
author Zhang, Haoran
Cha, Seohyeon
Beytur, Hasan Burhan
Chan, Kevin S
de Veciana, Gustavo
Vikalo, Haris
author_facet Zhang, Haoran
Cha, Seohyeon
Beytur, Hasan Burhan
Chan, Kevin S
de Veciana, Gustavo
Vikalo, Haris
contents Hierarchical inference systems route tasks across multiple computational layers, where each node may either finalize a prediction locally or offload the task to a node in the next layer for further processing. Learning optimal routing policies in such systems is challenging: inference loss is defined recursively across layers, while feedback on prediction error is revealed only at a terminal oracle layer. This induces a partial, policy-dependent feedback structure in which observability probabilities decay with depth, causing importance-weighted estimators to suffer from amplified variance. We study online routing for multi-layer hierarchical inference under long-term resource constraints and terminal-only feedback. We formalize the recursive loss structure and show that naive importance-weighted contextual bandit methods become unstable as feedback probability decays along the hierarchy. To address this, we develop a variance-reduced EXP4-based algorithm integrated with Lyapunov optimization, yielding unbiased loss estimation and stable learning under sparse and policy-dependent feedback. We provide regret guarantees relative to the best fixed routing policy in hindsight and establish near-optimality under stochastic arrivals and resource constraints. Experiments on large-scale multi-task workloads demonstrate improved stability and performance compared to standard importance-weighted approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2603_04247
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Online Learning for Multi-Layer Hierarchical Inference under Partial and Policy-Dependent Feedback
Zhang, Haoran
Cha, Seohyeon
Beytur, Hasan Burhan
Chan, Kevin S
de Veciana, Gustavo
Vikalo, Haris
Machine Learning
Artificial Intelligence
Hierarchical inference systems route tasks across multiple computational layers, where each node may either finalize a prediction locally or offload the task to a node in the next layer for further processing. Learning optimal routing policies in such systems is challenging: inference loss is defined recursively across layers, while feedback on prediction error is revealed only at a terminal oracle layer. This induces a partial, policy-dependent feedback structure in which observability probabilities decay with depth, causing importance-weighted estimators to suffer from amplified variance. We study online routing for multi-layer hierarchical inference under long-term resource constraints and terminal-only feedback. We formalize the recursive loss structure and show that naive importance-weighted contextual bandit methods become unstable as feedback probability decays along the hierarchy. To address this, we develop a variance-reduced EXP4-based algorithm integrated with Lyapunov optimization, yielding unbiased loss estimation and stable learning under sparse and policy-dependent feedback. We provide regret guarantees relative to the best fixed routing policy in hindsight and establish near-optimality under stochastic arrivals and resource constraints. Experiments on large-scale multi-task workloads demonstrate improved stability and performance compared to standard importance-weighted approaches.
title Online Learning for Multi-Layer Hierarchical Inference under Partial and Policy-Dependent Feedback
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2603.04247