Related papers: The VC-Dimension of Axis-Parallel Boxes on the Torus

Related papers

Uniform Laws of Large Numbers in Product Spaces [60.22626971185653]
We study uniform convergence phenomena in cartesian product spaces.<n>We show that a uniform law of large numbers holds for a family of events if and only if the linear VC dimension of the family is finite.
arXiv Detail & Related papers (2026-03-25T16:36:09Z)
Low-degree Lower bounds for clustering in moderate dimension [53.03724383992195]
We study the fundamental problem of clustering $n$ points into $K$ groups drawn from a mixture of isotropic Gaussians in $mathbbRd$.<n>We show that while the difficulty of clustering for $n leq dK$ is driven by dimension reduction and spectral methods, the moderate-dimensional regime involves more delicate phenomena leading to a "non-optimal rate"<n>We provide a novel non-spectral algorithm matching this rate, shedding new light on the computational limits of the clustering problem in moderate dimension.
arXiv Detail & Related papers (2026-02-26T14:03:55Z)
Learning the Intrinsic Dimensionality of Fermi-Pasta-Ulam-Tsingou Trajectories: A Nonlinear Approach using a Deep Autoencoder Model [0.0]
We find that the trajectories lie on a nonlinear manifold of dimension $mast = 2$ embedded in a $64$-dimensional phase space.<n>This dimensionality increases to $mast = 3$ at $= 1.1$, coinciding with a symmetry breaking transition.
arXiv Detail & Related papers (2026-01-27T12:59:29Z)
Sample Complexity of Agnostic Multiclass Classification: Natarajan Dimension Strikes Back [84.81507553557556]
We show that multiclass PAC sample complexity is governed by two distinct dimensions.<n>Unlike binary or online classification, multiclass learning inherently involves two structural parameters.<n>A key ingredient is a novel online procedure based on a self-adaptive multiplicative-weights algorithm performing a label-space reduction.
arXiv Detail & Related papers (2025-11-16T15:47:47Z)
Learning and Computation of $Φ$-Equilibria at the Frontier of Tractability [85.07238533644636]
$Phi$-equilibria is a powerful and flexible framework at the heart of online learning and game theory. We show that an efficient online algorithm incurs average $Phi$-regret at most $epsilon$ using $textpoly(d, k)/epsilon2$ rounds. We also show nearly matching lower bounds in the online setting, thereby obtaining for the first time a family of deviations that captures the learnability of $Phi$-regret.
arXiv Detail & Related papers (2025-02-25T19:08:26Z)
Online Epsilon Net and Piercing Set for Geometric Concepts [0.0]
We study the online $varepsilon$-net problem for geometric concepts with bounded VC-dimension. We present the first deterministic online algorithm with an optimal competitive ratio for intervals in $mathbbRd$. We also introduce a novel technique to analyze similar-sized objects of constant description complexity in $mathbbRd$.
arXiv Detail & Related papers (2024-10-09T16:58:36Z)
Winding Topology of Multifold Exceptional Points [0.0]
We characterize generic EP$n$s and symmetry-protected EP$n$s for arbitrary $n$. Our framework implies fundamental doubling theorems for both generic EP$n$s and symmetry-protected EP$n$s in $n$-band models.
arXiv Detail & Related papers (2024-09-13T19:14:56Z)
Symmetric Linear Bandits with Hidden Symmetry [17.40632789343385]
We study high-dimensional symmetric linear bandits where the symmetry is hidden from the learner. We provide a method based on model selection within the collection of low-dimensional subspaces.
arXiv Detail & Related papers (2024-05-22T18:11:57Z)
Transformers as Support Vector Machines [54.642793677472724]
We establish a formal equivalence between the optimization geometry of self-attention and a hard-margin SVM problem. We characterize the implicit bias of 1-layer transformers optimized with gradient descent. We believe these findings inspire the interpretation of transformers as a hierarchy of SVMs that separates and selects optimal tokens.
arXiv Detail & Related papers (2023-08-31T17:57:50Z)
Polynomial Width is Sufficient for Set Representation with High-dimensional Features [69.65698500919869]
DeepSets is the most widely used neural network architecture for set representation. We present two set-element embedding layers: (a) linear + power activation (LP) and (b) linear + exponential activations (LE)
arXiv Detail & Related papers (2023-07-08T16:00:59Z)
Small-time bilinear control of Schr\"odinger equations with application to rotating linear molecules [0.0]
We prove a small-time controllability property of nonlinear Schr"odinger equations on a d-dimensional torus $mathbbTd$. We focus on the 2-dimensional sphere $S2$, which models the bilinear control of a rotating linear top.
arXiv Detail & Related papers (2022-07-08T10:51:59Z)
Conditions for realizing one-point interactions from a multi-layer structure model [77.34726150561087]
A heterostructure composed of $N$ parallel homogeneous layers is studied in the limit as their widths shrink to zero. The problem is investigated in one dimension and the piecewise constant potential in the Schr"odinger equation is given.
arXiv Detail & Related papers (2021-12-15T22:30:39Z)
Eluder Dimension and Generalized Rank [48.27338656415236]
We show that eluder dimension can be exponentially larger than $sigma$-rank. When $sigma$ is the $mathrmrelu$ activation, we show that eluder dimension can be exponentially larger than $sigma$-rank.
arXiv Detail & Related papers (2021-04-14T16:53:13Z)
Binary strings of finite VC dimension [0.0]
In this paper we investigate subsets named by a predicate $P$ such that the relation $P(x+y)$ has finite VC dimension. We prove that strings of bounded VC dimension are meagre in the topology of the reals, provide simple rules for bounding the VC dimension of a string, and show that the bi-infinite strings of VC dimension $d$ are a non-so shift space.
arXiv Detail & Related papers (2021-01-16T17:51:52Z)
A deep network construction that adapts to intrinsic dimensionality beyond the domain [79.23797234241471]
We study the approximation of two-layer compositions $f(x) = g(phi(x))$ via deep networks with ReLU activation. We focus on two intuitive and practically relevant choices for $phi$: the projection onto a low-dimensional embedded submanifold and a distance to a collection of low-dimensional sets.
arXiv Detail & Related papers (2020-08-06T09:50:29Z)
The VC-dimension of k-vertex d-polytopes [1.0660480034605242]
We show that the VC-dimension of the class of $k$-vertex polytopes in $mathbb Rd$ is at most $8d2klogk$, answering an old question of Long and Warmuth.
arXiv Detail & Related papers (2020-04-09T23:00:08Z)
SU$(3)_1$ Chiral Spin Liquid on the Square Lattice: a View from Symmetric PEPS [55.41644538483948]
Quantum spin liquids can be faithfully represented and efficiently characterized within the framework of Projectedangled Pair States (PEPS) Characteristic features are revealed by the entanglement spectrum (ES) on an infinitely long cylinder. Special features in the ES are shown to be in correspondence with bulk anyonic correlations, indicating a fine structure in the holographic bulk-edge correspondence.
arXiv Detail & Related papers (2019-12-31T16:30:25Z)

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