arXiv research

Quantum models use complex Hilbert spaces for uncertainty.

Kernel Bayesian inference is a principled approach to nonparametric inference in probabilistic graphical models, where probabilistic relationships between variables are learned from data in a nonparametric manner. Various algorithms of kernel Bayesian inference have been developed by combining kernelized basic probabil…

A new method slices and sums radial kernels faster.

New Fourier features improve high-precision approximation in large-scale problems.

We obtain a Bernstein-type inequality for sums of Banach-valued random variables satisfying a weak dependence assumption of general type and under certain smoothness assumptions of the underlying Banach norm. We use this inequality in order to investigate in the asymptotical regime the error upper bounds for the broad …

This paper presents a convergence analysis of kernel-based quadrature rules in misspecified settings, focusing on deterministic quadrature in Sobolev spaces. In particular, we deal with misspecified settings where a test integrand is less smooth than a Sobolev RKHS based on which a quadrature rule is constructed. We pr…

Kernel Bayes' rule has been proposed as a nonparametric kernel-based method to realize Bayesian inference in reproducing kernel Hilbert spaces. However, we demonstrate both theoretically and experimentally that the prediction result by kernel Bayes' rule is in some cases unnatural. We consider that this phenomenon is i…

Unified quadrature framework for large-scale kernel machines.

Adaptive rule improves kernel-based gradient descent performance.

We study strictly proper scoring rules in the Reproducing Kernel Hilbert Space. We propose a general Kernel Scoring rule and associated Kernel Divergence. We consider conditions under which the Kernel Score is strictly proper. We then demonstrate that the Kernel Score includes the Maximum Mean Discrepancy as a special …

Optimal kernel sum classifiers analyzed for statistical efficiency.

Signature kernel scoring rule improves weather forecasting by capturing temporal and spatial dependencies.

New kernels on symmetric groups enable efficient Gaussian process sampling.

Predicts atomization energy with high accuracy using graph kernels and active learning.

Study integral kernels on complex symmetric spaces and their Dyson Brownian Motion applications.

Paper proposes a method for early stopping in regression using reproducing kernels.

A nonparametric kernel-based method for realizing Bayes' rule is proposed, based on representations of probabilities in reproducing kernel Hilbert spaces. Probabilities are uniquely characterized by the mean of the canonical map to the RKHS. The prior and conditional probabilities are expressed in terms of RKHS functio…

Improved kernel quadrature with convex weights using subsampling.

Improved kernel herding algorithm for faster quadrature rule convergence.

Paper solves a trading game for stocks that jump and diffuse, finding the Kelly rule is optimal.

Kernel method optimizes personalized dose rules for patients.

KSOS improves kernel learning for dynamical systems via global optimization.

Proposes a score to compare rule-based algorithms' interpretability.

The strategy of early stopping is a regularization technique based on choosing a stopping time for an iterative algorithm. Focusing on non-parametric regression in a reproducing kernel Hilbert space, we analyze the early stopping strategy for a form of gradient-descent applied to the least-squares loss function. We pro…

This note optimizes distributions using kernel mean embeddings with a new parameterization.

In this note we apply a 4-fold sum operation to develop an associativity rule for the pairwise symplectic sum. This allows us to show that certain diffeomorphic symplectic $4$-manifolds made out of elliptic surfaces are in fact symplectically deformation equivalent. We also show that blow-up points can be traded from o…

Defines a universal state sum construction for various TQFTs.

A novel Bayesian computation method using importance weighting improves numerical stability and performance.

Paper introduces a new kernel model for PSD-valued functions with theoretical guarantees and applications.

New bounds prevent degradation in high-dimensional signal estimation.

We discuss theoretical aspects of the product rule for classification problems in supervised machine learning for the case of combining classifiers. We show that (1) the product rule arises from the MAP classifier supposing equivalent priors and conditional independence given a class; (2) under some conditions, the pro…

Kernel-based quadrature rules are becoming important in machine learning and statistics, as they achieve super-$\sqrt{n}$ convergence rates in numerical integration, and thus provide alternatives to Monte Carlo integration in challenging settings where integrands are expensive to evaluate or where integrands are high d…

The present paper proposes generalized Gaussian kernel adaptive filtering, where the kernel parameters are adaptive and data-driven. The Gaussian kernel is parametrized by a center vector and a symmetric positive definite (SPD) precision matrix, which is regarded as a generalization of the scalar width parameter. These…

Novel Newton method for large-scale kernel methods using random features.

Analysis of deep neural networks under various learning rules reveals dynamics of feature and prediction learning.

We prove the statistical consistency of kernel Partial Least Squares Regression applied to a bounded regression learning problem on a reproducing kernel Hilbert space. Partial Least Squares stands out of well-known classical approaches as e.g. Ridge Regression or Principal Components Regression, as it is not defined as…

A Hilbert space embedding of a distribution---in short, a kernel mean embedding---has recently emerged as a powerful tool for machine learning and inference. The basic idea behind this framework is to map distributions into a reproducing kernel Hilbert space (RKHS) in which the whole arsenal of kernel methods can be ex…

Many leading classification algorithms output a classifier that is a weighted average of kernel evaluations. Optimizing these weights is a nontrivial problem that still attracts much research effort. Furthermore, explaining these methods to the uninitiated is a difficult task. Letting all the weights be equal leads to …

Distribution grids are currently challenged by frequent voltage excursions induced by intermittent solar generation. Smart inverters have been advocated as a fast-responding means to regulate voltage and minimize ohmic losses. Since optimal inverter coordination may be computationally challenging and preset local contr…

New invariants for Legendrian graphs defined and proven.

G-FIGS uses instance weights to create interpretable models from diverse data.

Defines a new algebra for singular foliations, extending Schwartz kernels.

Efficiently approximates kernel mean embeddings using Nyström method.

A novel kernel approach for model selection in simulator-based models.

A typical approach in estimating the learning rate of a regularized learning scheme is to bound the approximation error by the sum of the sampling error, the hypothesis error and the regularization error. Using a reproducing kernel space that satisfies the linear representer theorem brings the advantage of discarding t…

The article derives a novel Gram-Charlier A (GCA) Series based Extended Rule-of-Thumb (ExROT) for bandwidth selection in Kernel Density Estimation (KDE). There are existing various bandwidth selection rules achieving minimization of the Asymptotic Mean Integrated Square Error (AMISE) between the estimated probability d…

PSD models simplify probability density estimation.

Deep learning optimizes user association in Massive MIMO networks.