arXiv research

Paper analyzes iterative learning for concept classes and learns half-spaces.

In this paper we investigate what kind of manifolds arise as the total spaces of iterated $S^1$-bundles. A real Bott tower studied in \cite{CMO}, \cite{KM} and \cite{KN} is an example of an iterated $S^1$-bundle. We show that the total space of an iterated $S^1$-bundle is homeomorphic to an infra-nilmanifold. A real Bo…

Study Ricci iteration on spheres and projective spaces, proving existence and convergence.

Chen's iterated integrals are treated within synthetic differential geometry. The main result is that iterated integrals produce a subcomplex of the de Rham complex on the free path space as well as based path spaces.

On a smoothly stratified space, we identify intersection cohomology of any given perversity with an associated weighted $L^2$ cohomology for iterated fibred cusp metrics on the smooth stratum. In particular given a Witt space, we identify the $L^2$ cohomology of iterated fibred cusp metrics with the middle perversity i…

Stability of Einstein metrics under Ricci iteration studied.

In this paper we consider a problem of searching a space of predictive models for a given training data set. We propose an iterative procedure for deriving a sequence of improving models and a corresponding sequence of sets of non-linear features on the original input space. After a finite number of iterations N, the n…

Improved space management in iterative clustering reduces subset growth without sacrificing performance.

Algebraic knots are known to be iterated torus knots and to admit L-space surgeries. However, Hedden proved that there are iterated torus knots that admit L-space surgeries but are not algebraic. We present an infinite family of such examples, with the additional property that no nontrivial linear combination of knots …

The Ricci iteration is a discrete analogue of the Ricci flow. We give the first study of the Ricci iteration on a class of Riemannian manifolds that are not Kähler. The Ricci iteration in the non-Kähler setting exhibits new phenomena. Among them is the existence of so-called ancient Ricci iterations. As we show, these …

Improved stochastic Halpern iteration for fixed-point approximation in normed spaces.

Formal normal form created for real-smooth hypersurfaces.

The study analyzes how stochastic recursive algorithms converge to Markov chains.

We propose a novel method for maximum likelihood-based parameter inference in nonlinear and/or non-Gaussian state space models. The method is an iterative procedure with three steps. At each iteration a particle filter is used to estimate the value of the log-likelihood function at the current parameter iterate. Using …

XLVINs improve data efficiency in implicit planning by leveraging latent space.

FHBI enhances generalization in Bayesian inference with iterative steps in functional spaces.

Differential equations are derived for a continuous limit of iterated Schwarzian reflection of analytic curves, and solutions are interpreted as geodesics in an infinite-dimensional symmetric space geometry.

We bound the index of a subgroup in iterated Kodaira fibrations.

We consider trivializations of second iterated bundles of a Lie group that preserve lifted group structures. With such a trivialization, we elaborate Hamiltonian dynamics on cotangent, Lagrangian dynamics on tangent bundles and, both Hamiltonian and Lagrangian dynamics on Tulczyjew's symplectic space which is tangent o…

Study of Ricci iterations on Kähler metrics, proving new theorems.

New method uses iterated integrals to bridge geometric and homotopy information.

Paper solves DRO for continuous distributions with iterative algorithms.

This paper resolves equivariant K-theory for abelian actions.

Graph-based NAS improves sample efficiency in architecture design.

IBPF algorithm tackles high-dimensional parameter learning for complex systems.

Bayesian optimization tackles unknown search spaces with automatic expansion.

We construct a parallel transport on higher loop spaces of a manifold in term of a higher dimensional generalization of iterated path integrals. Under mild assumptions, we define a de Rham complex on higher loop spaces and we recover a known result of Hain of a de Rham structure on higher homotopy groups of a manifold.…

In a recent paper Donaldson defines three operators on a space of Hermitian metrics on a complex projective manifold: $T, T_ν, T_K.$ Iterations of these operators converge to balanced metrics, and these themselves approximate constant scalar curvature metrics. In this paper we investigate the convergence properties of …

We consider the problem of supervised learning with convex loss functions and propose a new form of iterative regularization based on the subgradient method. Unlike other regularization approaches, in iterative regularization no constraint or penalization is considered, and generalization is achieved by (early) stoppin…

In this paper we consider the dynamical system involved by the Ricci operator on the space of Kähler metrics. A. Nadel has defined an iteration scheme given by the Ricci operator for Fano manifold and asked whether it has some nontrivial periodic points. First, we prove that no such periodic points can exist. We define…

New properties of weighted Hilbert transform derived, useful for imaging applications.

Last-iterate guarantees for learning in co-coercive games under noisy feedback.

Faster WIND accelerates iterative BOND for LLM alignment.

Max-plus algebra approximates MDP value iteration for reduced state space.

For the multiple differential algebra of iterated differential forms (see math.DG/0605113 and math.DG/0609287) on a diffiety (O,C) an analogue of C-spectral sequence is constructed. The first term of it is naturally interpreted as the algebra of secondary iterated differential forms on (O,C). This allows to develop sec…

Study shows long-term flow on special manifolds with positive Yamabe constant.

Let X be a topological space. The homology of the iterated loop space $H_*Ω^n X$ is an algebra over the homology of the framed n-disks operad $H_*f\mathcal{D}_n$ \cite{Getzler:BVAlg,Salvatore-Wahl:FrameddoBVa}. We determine completely this $H_*f\mathcal{D}_n$-algebra structure on $H_*(Ω^n X;\mathbb{Q})$. We show that t…

New method for curve comparison using iterated integrals and moving frames.

Solves optimal stopping for Gauss-Markov bridges using time-space transformation.

ParK efficiently solves kernel ridge regression for large datasets.

In the preceding note math.DG/0610917 the $Λ_{k-1}\mathcal{C}$--spectral sequence, whose first term is composed of \emph{secondary iterated differential forms}, was constructed for a generic diffiety. In this note the zero and first terms of this spectral sequence are explicitly computed for infinite jet spaces. In par…

Policy gradient methods with aggregated states can achieve better performance than approximate policy iteration.

Sharp gradient estimates for a weighted p-Laplacian equation on metric measure spaces.

Study transforms discrete graph surfaces into smooth continua through iterative subdivision.

In this paper we consider successive iterations of the first-order differential operations in space ${\bf R}^3.$

Exponential distribution is ubiquitous in the framework of multi-agent systems. Usually, it appears as an equilibrium state in the asymptotic time evolution of statistical systems. It has been explained from very different perspectives. In statistical physics, it is obtained from the principle of maximum entropy. In th…

We give a rigorous construction of the path integral in N=1/2 supersymmetry as an integral map for differential forms on the loop space of a compact spin manifold. It is defined on the space of differential forms which can be represented by extended iterated integrals in the sense of Chen and Getzler-Jones-Petrack. Via…

We propose a novel adaptive learning algorithm based on iterative orthogonal projections in the Cartesian product of multiple reproducing kernel Hilbert spaces (RKHSs). The task is estimating/tracking nonlinear functions which are supposed to contain multiple components such as (i) linear and nonlinear components, (ii)…