Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits

• URL: http://arxiv.org/abs/2602.03970v2
• Date: Mon, 09 Feb 2026 22:59:16 GMT
• Title: Statistical Guarantees for Reasoning Probes on Looped Boolean Circuits
• Authors: Anastasis Kratsios, Giulia Livieri, A. Martina Neuman,
• Abstract summary: We study the statistical behaviour of reasoning probes in a stylized model of looped reasoning.<n>A reasoning probe has access to a sampled subset of internal nodes, possibly without covering the entire graph.<n>We show that, when the reasoning probe is parameterized by a graph convolutional network (GCN)-based hypothesis class and queries $N$ nodes, the worst-case generalization error attains the optimal rate.
• Score: 10.292476979020522
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We study the statistical behaviour of reasoning probes in a stylized model of looped reasoning, given by Boolean circuits whose computational graph is a perfect $ν$-ary tree ($ν\ge 2$) and whose output is appended to the input and fed back iteratively for subsequent computation rounds. A reasoning probe has access to a sampled subset of internal computation nodes, possibly without covering the entire graph, and seeks to infer which $ν$-ary Boolean gate is executed at each queried node, representing uncertainty via a probability distribution over a fixed collection of $\mathtt{m}$ admissible $ν$-ary gates. This partial observability induces a generalization problem, which we analyze in a realizable, transductive setting. We show that, when the reasoning probe is parameterized by a graph convolutional network (GCN)-based hypothesis class and queries $N$ nodes, the worst-case generalization error attains the optimal rate $\mathcal{O}(\sqrt{\log(2/δ)}/\sqrt{N})$ with probability at least $1-δ$, for $δ\in (0,1)$. Our analysis combines snowflake metric embedding techniques with tools from statistical optimal transport. A key insight is that this optimal rate is achievable independently of graph size, owing to the existence of a low-distortion one-dimensional snowflake embedding of the induced graph metric. As a consequence, our results provide a sharp characterization of how structural properties of the computational graph govern the statistical efficiency of reasoning under partial access.

Related papers

• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Sign Stochastic Gradient Descent [83.85536329832722]
  We solve the $k$-sparse parity problem with sign gradient descent (SGD) on two-layer fully-connected neural networks.<n>We show that this approach can efficiently solve the $k$-sparse parity problem on a $d$-dimensional hypercube.<n>We then demonstrate how a trained neural network with sign SGD can effectively approximate this good network, solving the $k$-parity problem with small statistical errors.
  arXiv  Detail & Related papers  (2024-04-18T17:57:53Z)
• Computational-Statistical Gaps in Gaussian Single-Index Models [77.1473134227844]
  Single-Index Models are high-dimensional regression problems with planted structure. We show that computationally efficient algorithms, both within the Statistical Query (SQ) and the Low-Degree Polynomial (LDP) framework, necessarily require $Omega(dkstar/2)$ samples.
  arXiv  Detail & Related papers  (2024-03-08T18:50:19Z)
• Planted Bipartite Graph Detection [13.95780443241133]
  We consider the task of detecting a hidden bipartite subgraph in a given random graph. Under the null hypothesis, the graph is a realization of an ErdHosR'enyi random graph over $n$ with edge density $q$. Under the alternative, there exists a planted $k_mathsfR times k_mathsfL$ bipartite subgraph with edge density $p>q$.
  arXiv  Detail & Related papers  (2023-02-07T18:18:17Z)
• Causal Bandits for Linear Structural Equation Models [58.2875460517691]
  This paper studies the problem of designing an optimal sequence of interventions in a causal graphical model. It is assumed that the graph's structure is known and has $N$ nodes. Two algorithms are proposed for the frequentist (UCB-based) and Bayesian settings.
  arXiv  Detail & Related papers  (2022-08-26T16:21:31Z)
• Bi-stochastically normalized graph Laplacian: convergence to manifold Laplacian and robustness to outlier noise [10.418647759223965]
  Bi-stochastic normalization provides an alternative normalization of graph Laplacians in graph-based data analysis. We prove the convergence of bi-stochastically normalized graph Laplacian to manifold (weighted-)Laplacian with rates. When the manifold data are corrupted by outlier noise, we theoretically prove the graph Laplacian point-wise consistency.
  arXiv  Detail & Related papers  (2022-06-22T21:08:24Z)
• Decentralized Sparse Linear Regression via Gradient-Tracking: Linear Convergence and Statistical Guarantees [23.256961881716595]
  We study a sparse linear regression over a network of agents, modeled as an undirected graph and no server node.<n>We analyze the convergence rate and statistical guarantees of a distributed projected gradient tracking-based algorithm.
  arXiv  Detail & Related papers  (2022-01-21T01:26:08Z)
• Distributed Sparse Regression via Penalization [5.990069843501885]
  We study linear regression over a network of agents, modeled as an undirected graph (with no centralized node) The estimation problem is formulated as the minimization of the sum of the local LASSO loss functions plus a quadratic penalty of the consensus constraint. We show that the proximal-gradient algorithm applied to the penalized problem converges linearly up to a tolerance of the order of the centralized statistical error.
  arXiv  Detail & Related papers  (2021-11-12T01:51:50Z)
• Inferring Hidden Structures in Random Graphs [13.031167737538881]
  We study the two inference problems of detecting and recovering an isolated community of emphgeneral structure planted in a random graph. We derive lower bounds for detecting/recovering the structure $Gamma_k$ in terms of the parameters $(n,k,q)$, as well as certain properties of $Gamma_k$, and exhibit computationally optimal algorithms that achieve these lower bounds.
  arXiv  Detail & Related papers  (2021-10-05T09:39:51Z)
• Optimal policy evaluation using kernel-based temporal difference methods [78.83926562536791]
  We use kernel Hilbert spaces for estimating the value function of an infinite-horizon discounted Markov reward process. We derive a non-asymptotic upper bound on the error with explicit dependence on the eigenvalues of the associated kernel operator. We prove minimax lower bounds over sub-classes of MRPs.
  arXiv  Detail & Related papers  (2021-09-24T14:48:20Z)
• Heavy-tailed Streaming Statistical Estimation [58.70341336199497]
  We consider the task of heavy-tailed statistical estimation given streaming $p$ samples. We design a clipped gradient descent and provide an improved analysis under a more nuanced condition on the noise of gradients.
  arXiv  Detail & Related papers  (2021-08-25T21:30:27Z)
• Testing correlation of unlabeled random graphs [18.08210501570919]
  We study the problem of detecting the edge correlation between two random graphs with $n$ unlabeled nodes. This is formalized as a hypothesis testing problem, where under the null hypothesis, the two graphs are independently generated. Under the alternative, the two graphs are edge-correlated under some latent node correspondence, but have the same marginal distributions as the null.
  arXiv  Detail & Related papers  (2020-08-23T19:19:45Z)
• Block-Approximated Exponential Random Graphs [77.4792558024487]
  An important challenge in the field of exponential random graphs (ERGs) is the fitting of non-trivial ERGs on large graphs. We propose an approximative framework to such non-trivial ERGs that result in dyadic independence (i.e., edge independent) distributions. Our methods are scalable to sparse graphs consisting of millions of nodes.
  arXiv  Detail & Related papers  (2020-02-14T11:42:16Z)

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.