Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models

• URL: http://arxiv.org/abs/2608.20183v1
• Date: Thu, 20 Aug 2026 15:40:50 GMT
• Title: Exact Algebraic Computation of Learning Coefficients for Two-Dimensional Singular Models
• Abstract summary: We present the first deterministic algorithm that computes local RLCT exactly for any two-dimensional computation whose Kullback-Leibler model is contact equivalent to a distance.<n>Our algorithm reveals exact structure in learning coefficients that sampling cannot and out-speeds it in the shallow regime.
• Score: 0.5735035463793009
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Classical information criteria such as the Bayesian Information Criterion (BIC) rely on regularity assumptions that break down for singular models, leading to incorrect model selection in settings such as deep learning. The Widely Applicable Bayesian Information Criterion (WBIC) relies on local learning coefficients $λ$, which in the analytic case coincides with local Real Log Canonical Thresholds (RLCT) of the Kullback-Leibler divergence of the model, to capture correct marginal likelihood asymptotics. Exact computation of the learning coefficients has been limited to special cases, and only sampling-based estimation methods are generally applicable. We present the first deterministic algorithm that computes local RLCTs exactly for any two-dimensional model whose Kullback-Leibler distance is contact equivalent to a polynomial, derive a bound on its complexity, and demonstrate its effectiveness for a broad class of models, with applications including polynomial neural networks. Beyond providing ground truth to calibrate sampling-based estimators, exact computation reveals algebraic structure in learning coefficients that sampling cannot and out-speeds it in the shallow regime.

Related papers

• Probabilistic Residual Learning for Online Recommendations [50.32543279885484]
  Probabilistic Residual Learning (PRL) is a causal Bayesian recommendation model that groups users for localized residual modeling.<n>PRL is compatible with various base deep learning recommender systems, improving their performance while automatically discovering meaningful user clusters.
  arXiv  Detail & Related papers  (2026-07-23T02:39:12Z)
• Efficient Covariance Estimation for Sparsified Functional Data [51.69796254617083]
  proposed Random-knots (Random-knots-Spatial) and B-spline (Bspline-Spatial) estimators of the covariance function are computationally efficient.<n>Asymptotic pointwise of the covariance are obtained for sparsified individual trajectories under some regularity conditions.
  arXiv  Detail & Related papers  (2025-11-23T00:50:33Z)
• Scaling and renormalization in high-dimensional regression [72.59731158970894]
  We present a unifying perspective on recent results on ridge regression.<n>We use the basic tools of random matrix theory and free probability, aimed at readers with backgrounds in physics and deep learning.<n>Our results extend and provide a unifying perspective on earlier models of scaling laws.
  arXiv  Detail & Related papers  (2024-05-01T15:59:00Z)
• A two stages Deep Learning Architecture for Model Reduction of Parametric Time-Dependent Problems [0.0]
  Parametric time-dependent systems are of crucial importance in modeling real phenomena. We present a general two-stages deep learning framework able to perform that generalization with low computational effort in time. Results are obtained applying the framework to incompressible Navier-Stokes equations in a cavity.
  arXiv  Detail & Related papers  (2023-01-24T11:24:18Z)
• GEC: A Unified Framework for Interactive Decision Making in MDP, POMDP, and Beyond [101.5329678997916]
  We study sample efficient reinforcement learning (RL) under the general framework of interactive decision making. We propose a novel complexity measure, generalized eluder coefficient (GEC), which characterizes the fundamental tradeoff between exploration and exploitation. We show that RL problems with low GEC form a remarkably rich class, which subsumes low Bellman eluder dimension problems, bilinear class, low witness rank problems, PO-bilinear class, and generalized regular PSR.
  arXiv  Detail & Related papers  (2022-11-03T16:42:40Z)
• Learning Single-Index Models with Shallow Neural Networks [43.6480804626033]
  We introduce a natural class of shallow neural networks and study its ability to learn single-index models via gradient flow. We show that the corresponding optimization landscape is benign, which in turn leads to generalization guarantees that match the near-optimal sample complexity of dedicated semi-parametric methods.
  arXiv  Detail & Related papers  (2022-10-27T17:52:58Z)
• Sparse Bayesian Learning for Complex-Valued Rational Approximations [0.03392423750246091]
  Surrogate models are used to alleviate the computational burden in engineering tasks. These models show a strongly non-linear dependence on their input parameters. We apply a sparse learning approach to the rational approximation.
  arXiv  Detail & Related papers  (2022-06-06T12:06:13Z)
• Supervised Multivariate Learning with Simultaneous Feature Auto-grouping and Dimension Reduction [7.093830786026851]
  This paper proposes a novel clustered reduced-rank learning framework. It imposes two joint matrix regularizations to automatically group the features in constructing predictive factors. It is more interpretable than low-rank modeling and relaxes the stringent sparsity assumption in variable selection.
  arXiv  Detail & Related papers  (2021-12-17T20:11:20Z)
• Optimal regularizations for data generation with probabilistic graphical models [0.0]
  Empirically, well-chosen regularization schemes dramatically improve the quality of the inferred models. We consider the particular case of L 2 and L 1 regularizations in the Maximum A Posteriori (MAP) inference of generative pairwise graphical models.
  arXiv  Detail & Related papers  (2021-12-02T14:45:16Z)
• Good Classifiers are Abundant in the Interpolating Regime [64.72044662855612]
  We develop a methodology to compute precisely the full distribution of test errors among interpolating classifiers. We find that test errors tend to concentrate around a small typical value $varepsilon*$, which deviates substantially from the test error of worst-case interpolating model. Our results show that the usual style of analysis in statistical learning theory may not be fine-grained enough to capture the good generalization performance observed in practice.
  arXiv  Detail & Related papers  (2020-06-22T21:12:31Z)
• Instability, Computational Efficiency and Statistical Accuracy [101.32305022521024]
  We develop a framework that yields statistical accuracy based on interplay between the deterministic convergence rate of the algorithm at the population level, and its degree of (instability) when applied to an empirical object based on $n$ samples. We provide applications of our general results to several concrete classes of models, including Gaussian mixture estimation, non-linear regression models, and informative non-response models.
  arXiv  Detail & Related papers  (2020-05-22T22:30:52Z)

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.