Group Theory
Papers
Fresh from arXiv, typeset properly. Highlighted words trade on the market.
Monday 4 May
This paper introduces gluing diagrams, a combinatorial tool to construct homomorphisms between the shift pseudogroups of directed graphs and thus also their full groups of shifts. We will establish which of these diagrams produce isomorphisms. As an application, using the interpretation of Higman-Thompson groups as full groups of shifts of specific graphs, we will describe a procedure that constructs gluing diagrams that explicitly describe the isomorphisms between Higman-Thompson groups, conjectured by Higman and whose existence was proven by Pardo arXiv:1006.1759. This procedure will follow Euclid's algorithm and will allow us to lift isomorphisms to higher arity.
Geometric Topology
Embedding complexes into pseudomanifolds
We show that for $d\geq 2$ every finite $d$-dimensional simplicial complex is a deformation retract of a $(2d-1)$-dimensional pseudomanifold with boundary. Moreover, it embeds as a retract in a closed $(2d-1)$-dimensional pseudomanifold.
Mathematical Physics · Cross-listed from hep-th
Open-Closed-Open Triality Beyond Matrix Models
We explore the ideas of open-closed-open triality within twisted holography. Starting from two transverse stacks of branes in the B-model on the resolved conifold, we obtain two equivalent open string descriptions. Both are full-fledged field theories. In the appropriate limit, they simplify to gauged $\beta\gamma$-systems with determinant insertions, as expected from open string field theory. The $\rho$-matrix models that have appeared previously in the literature appear from an on-shell analysis of the field-theory actions. Most importantly, we show that the effective potential generated by integrating out the open strings on the other stack of branes exactly captures their backreaction on the geometry. In particular, we match the action of the probe branes to that of giant gravitons in the $\textit{deformed}$ conifold. The second open string description of the triality thus directly diagnoses the emergent bulk spacetime.
Read the full abstract
Analysis of PDEs
Blow-up analysis and a priori bounds for NLS equations on metric graphs
We consider, on a connected metric graph $\mathcal{G}$, a family of nonlinear Schrödinger equations $$ -u'' + W_n(x) u + \lambda_n u = \rho_n(x)|u|^{p-2}u, \quad n \in \mathbb{N}. \qquad (*) $$ We assume that $p > 2$, $(W_n)$, $(\rho_n) \subseteq L^{\infty}(\mathcal{G})$ with $\rho_n \geq 0$, $|W_n|_{L^\infty(\mathcal{G})}$ and $|\rho_n|_{L^\infty(\mathcal{G})}$ are bounded and $\lambda_n \to +\infty$. Given $n \in \mathbb{N}$, we call "solution" a function $u_n \in H^1(\mathcal{G})$ which satisfies (*) for that $n\in \mathbb{N}$ together with the Kirchhoff conditions at the vertices. Focusing on the limiting behavior of sequences $(u_n) \subseteq H^1(\mathcal{G})$ of solutions as $\lambda_n \to + \infty$ and assuming that the Morse index $m(u_n)$ of $u_n$ is uniformly bounded, we establish, the existence of a finite subset of blow-up points away from which, up to a subsequence, $|u_n|$ has a global exponential decay. These points are generally a strict subset of the blow-up points, and their number is estimated by the bound on the Morse index of $(u_n)$. It is the first time that this global exponential decay property is established on graphs even if one consider only signed solutions. In the last part of the paper we derive various results of a priori bounds on the solutions in $L^\infty$ and $L^2$. Our blow-up analysis, combined with ODE arguments allows, for frequently considered classes of graphs, to obtain a fairly complete picture of the relationships between the number of nodal regions, Morse index, $L^\infty$ and $L^2$ norms of solutions.
Read the full abstract
Mathematical Physics · Cross-listed from quant-ph
Note on Strong Quantum Markov Properties
Quantum many-body Gibbs states satisfy an approximate local Markov property~\cite{chen2025GibbsMarkov}: local noise can be approximately recovered by a quasi-local recovery map, and the conditional mutual information decays for the corresponding tripartition. Recent work~\cite{bergamaschi2025structural} extends this property to approximate stationary states (metastable states) of certain master equations modeling system–bath dynamics, and proposes a strengthened post-selected recovery property requiring recovery to hold for each measurement outcome. In this note, we characterize this strong Markov property: it holds if and only if the state additionally satisfies correlation decay for suitable pairs of observables. We further prove several structural and operational consequences of the strong Markov property in the presence of an underlying master equation. First, one can estimate multiple observables from a single copy of the state via a repeated measurement–recovery protocol. Second, any two strongly Markov states must have local marginals that are either very close or well separated. Third, if a strongly Markov state can be expressed as a mixture of two strongly Markov states, then their local marginals must be nearly indistinguishable.
Read the full abstract
Statistics Theory
Uncountably many conditionally inaccessible decisions exist in every finite probability space
In a recent paper \cite{Redei-Jing2026} the notion of conditional $p$-inaccessibility of a decision based on utility maximization was defined and examples of conditionally $p$-inaccessible decisions were given. The conditional inaccessibility of a decision based on maximizing utility calculated by a probability measure $p^*$ expresses that the decision cannot be obtained if the expectation values of the utility functions are calculated using the (Jeffrey) conditional probability measure obtained by conditioning $p$ on partial evidence about the probability $p^*$ that determines the decision. The paper \cite{Redei-Jing2026} conjectured that conditionally $p$-inaccessible decisions exist in some probability spaces having arbitrary large finite number of elementary events. In this paper we prove that for any $p$ in any finite probability space there exist an uncountable number of probability measures $p^*$ for each of which there exist an uncountable number of pairs of utility functions that represent conditionally $p$-inaccessible decisions. If $p^*$ is an objective probability determining objectively good decisions and $p$ is the subjective probability determining a rational decision of a decision making Agent, the result says that there is an enormous number of decision situations in which the Agent's subjective probability prohibits the Agent's informed rational decision to be objectively good.
Read the full abstract
Statistics Theory
Characterizing Schur-concave commutative copulas as the closure of associative ones
Let $\mathcal{C}_a$ denote the class of associative copulas, and let $\overline{\mathcal{C}}_a$ be the closure, in the uniform metric $d_\infty$, of the convex hull of $\mathcal{C}_a$ . It is known that $\mathcal{C}_a \subseteq \mathcal{C}_{SC}$, the class of Schur-concave commutative copulas. We prove the reverse inclusion, establishing $\overline{\mathcal{C}}_a = \mathcal{C}_{SC}$.
Read the full abstract
Analysis of PDEs
Sharp regularity for degenerate fully nonlinear equations with oblique boundary conditions and Hamiltonian terms
We prove optimal boundary $C^{1,\alpha}$ regularity for viscosity solutions of degenerate fully nonlinear uniformly elliptic equations with oblique boundary conditions and Hamiltonian terms of the form \[ \begin{cases} |Du|^{\gamma}F(D^2 u) + \varrho(x)|Du|^{\sigma} = f(x) & \text{in } \Omega,\\ \beta(x)\cdot Du+\zeta(x)u = g(x) & \text{on } \partial \Omega, \end{cases} \] where $\gamma>0$ and $0<\sigma\le 1+\gamma$. We develop a compactness framework for affine translations, linking the size of the translation to the Hamiltonian structure. This is combined with a boundary improvement-of-flatness argument adapted to oblique boundary data, yielding the optimal boundary regularity.
Read the full abstract
Mathematical Physics · Cross-listed from hep-th
Landau levels via Jordan superalgebras
The goal of this note is to show that Jordan algebras and superalgebras provide an elegant and concise language for formulating quantum mechanical problems with inherent (super)conformal symmetry. The superconformal symmetries of the quantum MICZ-Kepler model and its dual oscillator realization in ${\mathbb R}^2$ are reviewed through the lens of the Tits-Kantor-Koecher correspondence: Kaplansky ${\mathfrak J} {\mathbb R}^{1|2}$ and Exceptional ${\mathfrak J} F^{6|4}$ Jordan superalgebras provide a natural framework for reconstructing (variously extended) superconformal algebras hidden in the Landau levels of an electron in an external magnetic field.
Read the full abstract
Rings and Algebras
Non-abelian extensions of Hom-Jacobi-Jordan algebras
This paper develops a cohomology theory for Hom-Jacobi-Jordan algebras using and applies it to classify non-abelian extensions. The main result establishes that equivalence classes of split extensions of a Hom-Jacobi-Jordan algebra $J$ by $V$ are in bijection with the second cohomology group $H^2(J,V)$, generalizing classical results from Lie and Leibniz algebra theory. We characterize extensions explicitly through 2-cocycles $(\rho, \theta)$ satisfying compatibility conditions, and provide complete classifications of low-dimensional cases.
Read the full abstract
Dynamical Systems
Combinatorics of Hamiltonian Normal Forms
We discuss algebraic and combinatorial aspects of the Hamiltonian normal form theory. The main objective is to describe the normal form near a singular point by an explicit formula in terms of the original Hamiltonian, avoiding the normalization procedure. In the case of one degree of freedom we compute the normal form as an explicit nonlinear functional, applied to the original Hamiltonian. In arbitrary dimension the corresponding formulas are more complicated but still explicit.
Read the full abstract
Optimization and Control
A second-order method landing on the Stiefel manifold via Newton$\unicode{x2013}$Schulz iteration
Retraction-free approaches offer attractive low-cost alternatives to Riemannian methods on the Stiefel manifold, but they are often first-order, which may limit the efficiency under high-accuracy requirements. To this end, we propose a second-order method landing on the Stiefel manifold without invoking retractions, which is proved to enjoy local quadratic (or superlinear for its inexact variant) convergence. The update consists of the sum of (i) a component tangent to the level set of the constraint-defining function that aims to reduce the objective and (ii) a component normal to the same level set that reduces the infeasibility. Specifically, we construct the normal component via Newton$\unicode{x2013}$Schulz, a fixed-point iteration for orthogonalization. Moreover, we establish a geometric connection between the Newton$\unicode{x2013}$Schulz iteration and Stiefel manifolds, in which Newton$\unicode{x2013}$Schulz moves along the normal space. For the tangent component, we formulate a modified Newton equation that incorporates Newton$\unicode{x2013}$Schulz. Numerical experiments on the orthogonal Procrustes problem, principal component analysis, and real-data independent component analysis illustrate that the proposed method performs better than the existing methods.
Read the full abstract
Algebraic Topology · Cross-listed from cs.LG
A Closed-Form Persistence-Landmark Pipeline for Certified Point-Cloud and Graph Classification
We introduce PLACE (Persistence-Landmark Analytic Classification Engine), a closed-form pipeline for classifying point clouds and graphs through their persistent-homology signatures. Three quantitative guarantees – a margin-based excess-risk rate, a closed-form descriptor-selection rule, and a per-prediction certificate – are derived from training labels alone, with no learned weights or held-out calibration. The embedding sums Mitra-Virk single-point coordinate functions over a sparse landmark grid; the closed-form weight rule $w_k^2 \propto (d_{k+1}^2 - d_k^2)/R_k^2$ maximizes the distortion slope in Mitra-Virk's affine certificate under $\nu$-coherence. (i) An $O(kR/(\Delta\sqrt{m_{\min}}))$ margin bound, driven by class-mean separation $\Delta$ and embedding radius $R$, matched in the sample-starved regime $m \lesssim R/\Delta$ by a Le Cam minimax lower bound. (ii) The Mahalanobis margin under Ledoit-Wolf-shrunk covariance is the strongest closed-form ranker on a 64-descriptor chemical-graph pool (mean Spearman $\rho = +0.56$ across 11 benchmarks, positive on 10 of 11); the isotropic surrogate $\Delta/\sqrt{\ell}$ admits a closed-form selection-consistency rate on the homogeneous protein/social pools. (iii) A training-time-decided certificate, with no per-prediction overhead, in three concrete radii (Pinelis, Gaussian plug-in, and variance-aware Pinelis-Bernstein). Empirically, PLACE is the strongest diagram-based method on Orbit5k and matches the strongest topology-based baseline within statistical noise on MUTAG and COX2; remaining gaps fall into two diagnosable regimes (descriptor blindness on NCI1/NCI109; pool-coverage limits elsewhere). The Pinelis-Bernstein radius fires on 8 of the 12 benchmarks; on MUTAG the empirical and population nearest-centroid rules agree on every one of 940 held-out test predictions, validating the certificate's mechanism.
Read the full abstract
Numerical Analysis
Asymptotic Plateaus for Generalized Abel Equations with Financial Applications
We develop a unified analytical and computational framework for the generalized Abel ordinary differential equation $y^{\prime }(x)=a_n(x)\bigl(% y^n+\lambda_{n-1}(x)y^{n-1}+\dots+\lambda_0(x)\bigr)$ of arbitrary degree $% n\ge1$ on the unbounded interval $[x_0,\infty)$. Under mild structural hypotheses on the coefficients and on the existence of a stable moving equilibrium branch $E(x)$, we prove a new Asymptotic Plateau Theorem establishing that the solution issued from $y(x_0)=0$ is globally defined, strictly monotone, trapped between zero and $E(x)$, and converges to a finite positive limit $L=\lim_{x\to\infty}E(x)$. We further obtain an explicit, computable rate of convergence and a degree-reduction principle that generalizes the classical Liouville substitution. The theory is complemented by a high-order Radau IIA implementation whose output reproduces the predicted plateaus to nine significant digits. A detailed application to a generalized Merton structural credit-risk model derives an Abel-type equation for the long-maturity state profile of the credit spread and illustrates the economic relevance of the framework.
Read the full abstract
Optimization and Control
Null Controllability for a Multi-Dimensional Degenerate Parabolic Equation with Degenerated Interior Point
In this study, we study the null controllability of a multi-dimensional degenerate parabolic equation characterized by a degenerate interior point. The control domain, which is an arbitrary inner region, does not encompass the degenerate point. To tackle this problem, we adopt a new approximation methodology. Specifically, we approximate the degenerate partial differential equations (PDEs) with a series of uniformly elliptic PDEs, notwithstanding their limited regularity. We then derive the Carleman estimate for these approximate uniformly parabolic equations and establish the observability inequality, which ultimately paves the way for demonstrating the null controllability of the system.
Read the full abstract
Dynamical Systems
Invariant measures for Deroin-Tholozan representations
We classify mapping class group invariant probability measures on the character varieties of Deroin-Tholozan representations, namely the compact components of relative $\mathrm{PSL}_2\mathbb{R}$-character varieties. We prove that an ergodic measure is either the counting measure on a finite orbit or agrees with the Liouville measure induced by the Goldman symplectic form. Our approach is based on measure disintegration along transverse Lagrangian tori fibrations.
Read the full abstract
Dynamical Systems · Cross-listed from econ.TH
Equilibrium Stability and Uniqueness with a Large Number of Commodities and Patient Consumers
We show that a large effective number of commodities can be a source of equilibrium stability and uniqueness: expanding substitution opportunities strengthens aggregate substitution effects. We study finite dated-commodity exchange economies obtained by truncating a countably infinite-horizon environment with discounted, additively separable utilities. In this setting, the effective number of commodities is the discounted count of dated commodities, so greater patience makes distant commodities more relevant. With an appropriate normalization, equilibrium substitution effects accumulate at the rate of the effective number of commodities. When a preference diversification condition holds, equilibrium income effects grow at a lower rate. The condition is satisfied, for example, when agents have sparse or localized taste differences across commodities, or when their taste profiles become sufficiently heterogeneous as the commodity space expands. Hence, whenever the effective number of commodities is sufficiently large, every equilibrium is locally tâtonnement stable, which in turn implies equilibrium uniqueness.
Read the full abstract
Mathematical Physics
On Algebras of Functions over Infinite Dimensions
We introduce a family of reproducing kernel Hilbert spaces $\mathcal A_\Lambda$ of holomorphic functions defined on an infinite–dimensional domain in a separable Hilbert space, $\mathbb{H}$. The reproducing kernel of $\mathcal A_\Lambda$ is constructed using the covariance operator associated with a Gaussian measure on $\mathbb{H}$, along with a holomorphic function $\Lambda$ on the unit disk. Under certain conditions on the kernel, $\mathcal A_\Lambda$ is closed under pointwise multiplication, giving it the structure of a reproducing kernel Hilbert algebra (RKHA). We also study twisted canonical commutation relations on these RKHAs, where the creation and annihilation operators are both bounded.
Read the full abstract
Optimization and Control
Statistical Inference of Day-to-Day Traffic Dynamics
Day-to-day traffic dynamics are widely used to model flow evolution due to travelers' learning and adjustment behavior, yet empirical analysis of these models often relies on descriptive calibration with limited inferential content. This paper develops a statistical inference framework for day-to-day route choice dynamics based on a stochastic individual-level adjustment model. The framework enables uncertainty quantification and formal inference for behavioral parameters from trajectory data. We establish identifiability and consistency under mild conditions, and extend the framework to accommodate demand variation, user heterogeneity through a hierarchical structure, and anonymized observability caused by privacy constraints on trajectory data. Simulation studies demonstrate good finite-sample performance, calibrated uncertainty, and robustness to model misspecification. Empirical analyses of controlled laboratory experiments and real-world trajectory data from Ann Arbor, Michigan, show that the framework can generate novel behavioral insights across settings: it reveals the inadequacy of a purely inter-day learning model once en-route information is introduced, recovers systematic behavioral differences across participant types, and uncovers meaningful day-to-day learning together with substantial demand variation in real-world commuting behavior.
Read the full abstract
Numerical Analysis
Factorization and monotonicity methods for reconstructing impenetrable obstacles in inverse biharmonic scattering
The inverse scattering problem for biharmonic waves, governing flexural vibrations of elastic plates, presents fundamental analytical challenges distinct from acoustic inverse problems due to the fourth-order differential operator and higher-order boundary conditions. This paper addresses the reconstruction of impenetrable obstacles with Dirichlet or Neumann boundary conditions from far-field measurements. We establish new factorizations of the far-field operator by considering structures of the biharmonic fundamental solution and the boundary conditions. We rigorously prove that the factorizations satisfy the range identities and derive characterizations of the obstacle's support by the factorization methods, valid for all wavenumbers except the associated transmission eigenvalues. Furthermore, we establish a monotonicity relation for the eigenvalues of the far-field operator, which yields an alternative characterization of the obstacle's support that remains applicable for all wavenumbers. Numerical experiments for the Dirichlet obstacles with various shapes are presented to demonstrate the effectiveness and robustness of the proposed reconstruction schemes.
Read the full abstract
Numerical Analysis
Two-scale Neural Networks for Singularly Perturbed Dynamical Systems with Multiple Parameters
We extend our two-scale neural-network method for scalar singularly perturbed problems with one small parameter to dynamical systems with multiple small parameters. To accommodate multiple small parameters, we use a single effective scale parameter defined as the geometric mean of all parameters. We thus augment the network input with a scale-aware feature, enabling it to capture sharp solution transitions intrinsically. Numerical experiments across a range of dynamical systems demonstrate that the proposed framework can handle coupled systems with multiple and high-contrast small parameters and obtain satisfactory accuracy in capturing solution features induced by small parameters.
Read the full abstract
Analysis of PDEs
Quantitative Weak Unique Continuation on Annular Domains for Backward Degenerate Parabolic Equations with Degenerate Interior Points
In this paper, we establish a quantitative weak unique continuation theorem on an annular domain for a backward degenerate parabolic equation with a degenerate interior point. Our methodology hinges on approximating the solution of the degenerate parabolic equation through solutions of non-degenerate parabolic counterparts. Subsequently, we establish Carleman estimates for the non-degenerate parabolic equation across two separate domains. By virtue of these estimates, we deduce a quantitative weak unique continuation property for the degenerate parabolic equation, thereby substantiating the weak unique continuation result for the original degenerate parabolic equation.
Read the full abstract
Combinatorics
Ramsey numbers and Gallai–Ramsey numbers of disjoint unions of cherries
For graphs $G_1,\ldots,G_k$, the Ramsey number $R(G_1,\ldots,G_k)$ is the smallest positive integer $N$ such that every $k$-edge-coloring of $K_N$ contains a monochromatic copy of $G_i$ in color $i$ for some $i\in[k]$. The Gallai–Ramsey number $GR(G_1,\ldots,G_k)$ is defined analogously, with the colorings restricted to Gallai colorings (i.e., edge-colorings with no rainbow triangle). A copy of $P_3$ is called a cherry. Let $n_iP_3$ denote the disjoint union of $n_i$ cherries. Wu, Magnant, Nowbandegani, and Xia (Discrete Appl. Math., 2019) proposed two conjectures: \[ R(n_1P_3,\ldots,n_kP_3)=N\ \text{and}\ GR(n_1P_3,\ldots,n_kP_3)=N\,, \] where $N=2\max\{n_1,\ldots,n_k\}+\sum_{i=1}^kn_i-k+1$. We disprove the Ramsey conjecture and provide some sufficient conditions for determining the exact value of $R(n_1P_3,\ldots,n_kP_3)$. In contrast, we confirm the Gallai–Ramsey conjecture.
Read the full abstract
Optimization and Control
Risk-Averse Ensemble Control for Control-Affine Systems
A number of important modern applications in optimal control can be formulated as open loop control problems in which the underlying dynamical systems are subject to random inputs. These so-called ensemble control problems require the corresponding optimal control to be deterministic, as it must be computed before the realization of uncertainty and the passage of time. Practical applications of ensemble control include quantum control and the training of Neural ODEs. However, the standard approach to ensemble control treats the uncertainty in the objective function via the expectation, which provides optimal controls that only work well on average while ignoring critical outlier phenomena. This study provides a comprehensive mathematical treatment of risk-averse ensemble control. Within this setting, we adopt a control-affine structure that ensures the lower semi-continuity needed for proving the existence of optimal solutions. The central analytical contribution of this paper is a rigorous characterization of the control-to-state mapping in which we establish weak-to-strong continuity, continuous Fréchet differentiability, and weak-to-strong continuity of the derivative operator. Furthermore, this regularity yields primal and dual first-order optimality conditions characterized by an adjoint state of bounded variation, and it fulfills the functional prerequisites required for the convergence of infinite dimensional optimization algorithms. We conclude by validating these theoretical developments through a numerical experiment in quantum control.
Read the full abstract
Geometric Topology
Double twist knots and lattice paths
In this work, we explore the combinatorics arising from the quiver generating series of the unreduced $r$-colored HOMFLY-PT polynomial $\bar{P}_r(a,q)$ for some twist-knots and double twist knots. By taking the limit $a = 0$ and $q = 1$, we indeed obtain lattice path models for these knots.
Read the full abstract
Analysis of PDEs
A Shape Design Approximation for Degenerate Partial Differential Equations and Its Application
In this paper, we focus on two types of degenerate partial differential equations: a degenerate elliptic equation and a degenerate parabolic equation. Significantly, both categories are characterized by the same principal operator. To obtain solutions for these equations, we introduce a novel approximation approach, termed the shape design approximation. As a practical application of this method, we derive a Carleman estimate for the backward degenerate parabolic equation. This estimate plays a pivotal role in establishing the null controllability of the degenerate parabolic equation. A notable advantage of employing the shape design approximation in deriving the Carleman estimate is that it enables us to bypass the requirement for second order derivatives in the degenerate equation. Usually, this has been a significant obstacle in the derivation of Carleman estimates for degenerate parabolic equations.
Read the full abstract
Operator Algebras
Uniqueness of almost periodic outer flows on the hyperfinite type $\mathrm{II}_1$ factor
We show that any almost periodic outer flow $\alpha : \mathbb R \curvearrowright R$ on the hyperfinite type $\mathrm{II}_1$ factor with Connes' spectrum $\Gamma(\alpha) = \mathbb R$ satisfies the Rokhlin property and thus is unique up to cocycle conjugacy. The proof relies on a key cocycle perturbation result for type $\mathrm{III}$ amenable equivalence relations. As a byproduct of our methods, we also show that every almost periodic factor of type $\mathrm{III}_1$ with separable predual has an extremal almost periodic faithful normal state.
Read the full abstract
Analysis of PDEs
An Inverse Source Problem For a Time-Fractional Mixed Wave-Diffusion-Wave Equation in a Cylindrical Domain
This paper addresses the inverse source problem for a mixed-type fractional wave-diffusion-wave equation posed in a cylindrical domain. The governing equation involves a time-dependent variable-order fractional derivative, which enables the model to effectively capture temporal transitions between wave-like and diffusive behaviors. The solution is constructed in the form of a Fourier-Bessel series. By employing the method of separation of variables together with fundamental properties of Bessel functions, we analyze the uniform convergence of the resulting infinite series. This analysis ultimately leads to a rigorous proof of the existence of a solution.
Read the full abstract
Algebraic Geometry
$K$-holomorphic functions with definable real part
Let $R$ be a real closed field and $K:=R(i)$ its algebraic closure. Let $U\subset K^n$ be an open and definable set in a fixed o-minimal structure. In this note, we study the relationship between definability of a $K$-holomorphic function $f=f_1+if_2:U\to K$ and the definability and (strong) $R$-analyticity of its real part $f_1:U\to R$. Our results turn out to be the best possible {in general}, and their precision depends on the considered o-minimal structure. We obtain a complete characterisation in the semialgebraic case.
Read the full abstract
Probability
Universality in Deep Neural Networks: An approach via the Lindeberg exchange principle
We consider the infinite-width limit of a fully connected deep neural network with general weights, and we prove quantitative general bounds on the $2$-Wasserstein distance between the network and its infinite-width Gaussian limit, under appropriate regularity assumptions on the activation function. Our main tool is a Lindeberg principle for Deep Neural Networks, which we use to successively replace the weights on each layer by Gaussian random variables.