Brownian Kernel Ladders

• URL: http://arxiv.org/abs/2606.15812v1
• Date: Sun, 14 Jun 2026 13:27:28 GMT
• Title: Brownian Kernel Ladders
• Abstract summary: We introduce Brownian kernel ladders (BKLs), a hierarchy of integral reproducing kernel Hilbert spaces.<n>We show that BKL spaces form quasi-Banach spaces, satisfy depth-dependent Hlder regularity estimates, and exhibit strict monotonicity with respect to depth.<n>Our results provide a mathematically tractable hierarchical function-space framework for studying compositional representations in deep learning.
• Score: 3.924521334514384
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Constructing mathematically tractable function spaces that capture hierarchical compositional representations remains a central challenge in statistical learning theory. We introduce Brownian kernel ladders (BKLs), a recursively defined hierarchy of integral reproducing kernel Hilbert spaces generated through Brownian-kernel integral constructions. Starting from linear functionals, each layer is obtained by integrating Brownian kernels over probability measures supported on subsets of the previous layer, yielding a recursive function-space model in which depth is encoded directly through the hierarchy. Based on this framework, we define canonical BKL spaces together with an associated complexity functional. We establish several analytical and statistical properties of these spaces. In particular, we show that BKL spaces form quasi-Banach spaces, satisfy depth-dependent Hölder regularity estimates, and exhibit strict monotonicity with respect to depth. We further prove existence results for regularized empirical risk minimization and derive Gaussian complexity bounds that remain uniformly controlled with respect to both the ambient dimension and the hierarchy depth. A key ingredient of the analysis is a combinatorial proof technique based on recursive subset decompositions and Brownian-kernel threshold representations. These estimates yield excess-risk guarantees of near-parametric order for regularized empirical risk minimization over BKL spaces. Our results provide a mathematically tractable hierarchical function-space framework for studying compositional representations in deep learning.

Related papers

• Operator-Theoretic Generalization Bounds for Multitask Deep Learning [0.0254890465057467]
  We develop operator-theoretic generalization bounds for deep multi-output function classes.<n>We derive Rademacher bounds complexity for invertible and width-expanding injective architectures.
  arXiv  Detail & Related papers  (2026-08-17T00:36:57Z)
• Variation Brownian Kernel Ladders [0.0]
  We introduce the emphVariation Brownian Kernel Ladder (VBKL), a path-atomic function-space framework.<n>Starting from linear projections, each atom composes unit-ball profiles from the Brownian reproducing kernel Hilbert space.<n>The full VBKL space is then the signed-measure variation hull of the completed dictionary.
  arXiv  Detail & Related papers  (2026-08-14T02:15:08Z)
• An RKHS Perspective on Tree Ensembles [0.0]
  We develop a theoretical framework for analyzing Random Forests and Gradient Boosting.<n>We show that a Random Forest predictor can be characterized as the unique minimizer of a penalized empirical risk functional.<n>A key feature of this framework is that both the kernel and the RKHS geometry are data-dependent, offering a theoretical explanation for the strong empirical performance of tree-based ensembles.
  arXiv  Detail & Related papers  (2025-11-29T08:54:37Z)
• A Derandomization Framework for Structure Discovery: Applications in Neural Networks and Beyond [25.592330047318274]
  We focus on the structure discovery aspect and study it under weaker assumptions.<n>At the core of our approach is a key $textitderandomization$ lemma.<n>This lemma directly explains structure discovery and has immediate applications in other domains.
  arXiv  Detail & Related papers  (2025-10-22T08:55:00Z)
• Graph-based Clustering Revisited: A Relaxation of Kernel $k$-Means Perspective [73.18641268511318]
  We propose a graph-based clustering algorithm that only relaxes the orthonormal constraint to derive clustering results.<n>To ensure a doubly constraint into a gradient, we transform the non-negative constraint into a class probability parameter.
  arXiv  Detail & Related papers  (2025-09-23T09:14:39Z)
• Why and When Deep is Better than Shallow: An Implementation-Agnostic State-Transition View of Depth Supremacy [15.310099705870114]
  We formulate a deep model as an abstract state-transition semigroup acting on a general metric space.<n>We separate the implementation (e.g., ReLU nets, transformers, and chain-of-thought) from the abstract state transition.<n>We prove a bias-variance decomposition in which the dependence depends only on the abstract depth-$k$ network and not on the implementation.
  arXiv  Detail & Related papers  (2025-05-21T03:32:30Z)
• On The Sample Complexity Bounds In Bilevel Reinforcement Learning [49.19950489963245]
  Bilevel reinforcement learning (BRL) has emerged as a powerful framework for aligning generative models.<n>We present the first sample of $mathcalO(epsilon)$ in continuous state-action complexity.<n>Our analysis also extends complexity improving upon existing bounds of $mathcalO(epsilon)$.
  arXiv  Detail & Related papers  (2025-03-22T04:22:04Z)
• Finding Alignments Between Interpretable Causal Variables and Distributed Neural Representations [62.65877150123775]
  Causal abstraction is a promising theoretical framework for explainable artificial intelligence. Existing causal abstraction methods require a brute-force search over alignments between the high-level model and the low-level one. We present distributed alignment search (DAS), which overcomes these limitations.
  arXiv  Detail & Related papers  (2023-03-05T00:57:49Z)
• Ensemble forecasts in reproducing kernel Hilbert space family [0.0]
  A methodological framework for ensemble-based estimation and simulation of high dimensional dynamical systems is proposed. To that end, the dynamical system is embedded in a family of reproducing kernel Hilbert spaces (RKHS) with kernel functions driven by the dynamics.
  arXiv  Detail & Related papers  (2022-07-29T12:57:50Z)
• Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency [111.83670279016599]
  We study reinforcement learning for partially observed decision processes (POMDPs) with infinite observation and state spaces. We make the first attempt at partial observability and function approximation for a class of POMDPs with a linear structure.
  arXiv  Detail & Related papers  (2022-04-20T21:15:38Z)
• Lattice-Based Methods Surpass Sum-of-Squares in Clustering [98.46302040220395]
  Clustering is a fundamental primitive in unsupervised learning. Recent work has established lower bounds against the class of low-degree methods. We show that, perhaps surprisingly, this particular clustering model textitdoes not exhibit a statistical-to-computational gap.
  arXiv  Detail & Related papers  (2021-12-07T18:50:17Z)
• Provable Hierarchy-Based Meta-Reinforcement Learning [50.17896588738377]
  We analyze HRL in the meta-RL setting, where learner learns latent hierarchical structure during meta-training for use in a downstream task. We provide "diversity conditions" which, together with a tractable optimism-based algorithm, guarantee sample-efficient recovery of this natural hierarchy. Our bounds incorporate common notions in HRL literature such as temporal and state/action abstractions, suggesting that our setting and analysis capture important features of HRL in practice.
  arXiv  Detail & Related papers  (2021-10-18T17:56:02Z)

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.