Optimal Rates for Agentic Networked Information Aggregation
Researchers close the Kearns–Roth–Ryu gap for agentic networked information aggregation, proving excess error is constant up to depth M^2 then Θ(M^2/D).
The paper studies a networked learning model where agents in a DAG each see only a subset of features and pass only their predictions forward. It sharpens the earlier lower bound to Ω(√(M/D)) for depth below M^2 and constructs M-covered paths of depth D ≥ M^2 achieving Ω(M^2/D) excess error, establishing the correct rate for both regression and logistic classification. It also shows excess error contracts geometrically along the path for any fixed distribution, ruling out a single instance that witnesses polynomial lower bounds at every depth.
- Proves optimal rate: constant up to depth M^2, Θ(M^2/D) beyond
- Improves cyclic-instance lower bound to Ω(√(M/D))
- Extends optimal rate to logistic classification under BCE logit-passing
- Shows geometric contraction of excess error along paths for fixed distributions
- Tags
- agentic-aiclassificationgeneralization-boundsinformation-aggregationmulti-agent-learningregressionstatistical-learning
- Vendors
- arXiv
- Organizations
- Kearns, Roth, and RyuBateni et al.
From the original article
1 min read at arxiv.orgBuilding on the pioneering paper of Kearns, Roth, and Ryu (SODA'26), we study information aggregation in a networked learning model. The model captures a central pattern in agentic AI: each agent sees only part of the data and passes on only its own conclusion. Their model considers a linear regression problem with the mean squared error (MSE) loss.
By MohammadHossein Bateni · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.