Optimal Rates for Agentic Networked Information Aggregation

• URL: http://arxiv.org/abs/2609.05318v1
• Date: Fri, 04 Sep 2026 16:12:16 GMT
• Title: Optimal Rates for Agentic Networked Information Aggregation
• Abstract summary: We study information aggregation in a networked learning model.<n>Agents sit in a DAG and each sees only a subset of the features and its parents' predictions, fits a linear predictor, and passes only its prediction forward.<n>We prove the same optimal rate for logistic classification in the logit-passing model of Bateni et al.
• Score: 14.181355030230309
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building 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. Agents sit in a DAG and each sees only a subset of the features and its parents' predictions, fits a linear predictor, and passes only its prediction forward. The benchmark is the full-feature learner that sees all raw features. A path of depth $D$ is $M$-covered if every block of $M$ consecutive agents collectively sees all raw features. Kearns, Roth, and Ryu proved that the excess mean squared error of the last agent on such a path is $O(M/\sqrt D)$, and gave a cyclic instance with excess error $Ω(M/D)$ for $D<M^2$. We close this gap: the correct rate is constant up to depth $M^2$, and $Θ(M^2/D)$ beyond it. We first give a sharper analysis of the cyclic instance and improve its lower bound to $Ω(\sqrt{M/D})$ for $D<M^2$. We then construct, for every depth $D\ge M^2$, an $M$-covered path of depth $D$ with excess error $Ω(M^2/D)$. The same instance gives the constant lower bound for all $D < M^2$. We also show that for any fixed distribution the excess error contracts geometrically along the path, ruling out any single instance that witnesses any polynomial lower bound at every depth. Finally, we prove the same optimal rate for logistic classification in the logit-passing model of Bateni et al., which considers the binary cross-entropy (BCE) loss. The same improved upper bound of $O(M^2/D)$ holds, and we transfer all the regression lower bounds by showing that on those examples the logistic path follows the least-squares path up to rescaling.

Related papers

• Optimal Lower Bounds for Networked Information Aggregation [3.130458422860269]
  Networked information aggregation on a gaussian instance in our worst case family incurs an $ell$-error lower bounded by $(1/sqrtD)$ with respect to the ideal predictor.
  arXiv  Detail & Related papers  (2026-08-16T01:36:33Z)
• Optimal Reconstruction from Linear Queries [22.749520200232624]
  We study the problem of reconstructing an unknown point in $mathbbRd$ from approximate linear queries.<n>This setting arises naturally in applications ranging from low-dimensional remote sensing and signal recovery to high-dimensional data analysis and privacy-sensitive inference.
  arXiv  Detail & Related papers  (2026-05-19T10:04:37Z)
• The Hidden Width of Deep ResNets: Tight Error Bounds and Phase Diagrams [15.246178589173523]
  We study the gradient-based training of large-depth residual networks (ResNets)<n>We show that with a diverging depth $L$, a fixed embedding dimension $D$, and an arbitrary hidden width $M$, the training dynamics converges to a Neural Mean ODE training dynamics.
  arXiv  Detail & Related papers  (2025-09-12T11:51:44Z)
• Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback [49.84060509296641]
  We study online finite-horizon Markov Decision Processes with adversarially changing loss and aggregate bandit feedback (a.k.a full-bandit)<n>Under this type of feedback, the agent observes only the total loss incurred over the entire trajectory, rather than the individual losses at each intermediate step within the trajectory.<n>We introduce the first Policy Optimization algorithms for this setting.
  arXiv  Detail & Related papers  (2025-02-06T12:03:24Z)
• Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit [75.4661041626338]
  We study the problem of gradient descent learning of a single-index target function $f_*(boldsymbolx) = textstylesigma_*left(langleboldsymbolx,boldsymbolthetarangleright)$<n>We prove that a two-layer neural network optimized by an SGD-based algorithm learns $f_*$ with a complexity that is not governed by information exponents.
  arXiv  Detail & Related papers  (2024-06-03T17:56:58Z)
• Convergence Analysis of Probability Flow ODE for Score-based Generative Models [5.939858158928473]
  We study the convergence properties of deterministic samplers based on probability flow ODEs from both theoretical and numerical perspectives.<n>We prove the total variation between the target and the generated data distributions can be bounded above by $mathcalO(d3/4delta1/2)$ in the continuous time level.
  arXiv  Detail & Related papers  (2024-04-15T12:29:28Z)
• Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition [71.33787410075577]
  We study reinforcement learning with linear function approximation, unknown transition, and adversarial losses. We propose a new algorithm that attains an $widetildeO(dsqrtHS3K + sqrtHSAK)$ regret with high probability.
  arXiv  Detail & Related papers  (2024-03-07T15:03:50Z)
• Horizon-Free and Variance-Dependent Reinforcement Learning for Latent Markov Decision Processes [62.90204655228324]
  We study regret minimization for reinforcement learning (RL) in Latent Markov Decision Processes (LMDPs) with context in hindsight. We design a novel model-based algorithmic framework which can be instantiated with both a model-optimistic and a value-optimistic solver.
  arXiv  Detail & Related papers  (2022-10-20T21:32:01Z)
• Provably Efficient Offline Reinforcement Learning with Trajectory-Wise Reward [66.81579829897392]
  We propose a novel offline reinforcement learning algorithm called Pessimistic vAlue iteRaTion with rEward Decomposition (PARTED) PARTED decomposes the trajectory return into per-step proxy rewards via least-squares-based reward redistribution, and then performs pessimistic value based on the learned proxy reward. To the best of our knowledge, PARTED is the first offline RL algorithm that is provably efficient in general MDP with trajectory-wise reward.
  arXiv  Detail & Related papers  (2022-06-13T19:11:22Z)
• Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond [20.518134448156744]
  Gradual domain adaptation (GDA) assumes a path of $(T-1)$ unlabeled intermediate domains bridging the source and target. We prove a significantly improved generalization bound as $widetildeOleft(varepsilon_0+Oleft(sqrtlog(T)/nright)$, where $Delta$ is the average distributional distance between consecutive domains.
  arXiv  Detail & Related papers  (2022-04-18T07:39:23Z)
• Variance-Aware Confidence Set: Variance-Dependent Bound for Linear Bandits and Horizon-Free Bound for Linear Mixture MDP [76.94328400919836]
  We show how to construct variance-aware confidence sets for linear bandits and linear mixture Decision Process (MDP) For linear bandits, we obtain an $widetildeO(mathrmpoly(d)sqrt1 + sum_i=1Ksigma_i2) regret bound, where $d is the feature dimension. For linear mixture MDP, we obtain an $widetildeO(mathrmpoly(d)sqrtK)$ regret bound, where
  arXiv  Detail & Related papers  (2021-01-29T18:57:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.