Proposes an efficient method for GPLVM with arbitrary kernels.
problem GPLVM's limitation with standard kernel functions and computational bottlenecks.
method Uses the unscented transformation to handle arbitrary kernels efficiently.
result Comparable or better performance with linear computational complexity.
Learning linear combinations of multiple kernels is an appealing strategy when the right choice of features is unknown. Previous approaches to multiple kernel learning (MKL) promote sparse kernel combinations to support interpretability and scalability. Unfortunately, this 1-norm MKL is rarely observed to outperform tr…
We present in this work a new family of kernels to compare positive measures on arbitrary spaces $\Xcal$ endowed with a positive kernel κ, which translates naturally into kernels between histograms or clouds of points. We first cover the case where $\Xcal$ is Euclidian, and focus on kernels which take into account th…
Paper tackles matrix estimation under arbitrary noise, achieving minimax optimality.
problem Noisy low-rank-plus-sparse matrix recovery under arbitrary dependence.
method Incoherent-constrained least-square estimator, novel energy spreading result.
result Achieves minimax optimality in estimating structured Markov transition kernels.
Kernel methods have been widely applied to machine learning and other questions of approximating an unknown function from its finite sample data. To ensure arbitrary accuracy of such approximation, various denseness conditions are imposed on the selected kernel. This note contributes to the study of universal, characte…
A graph product kernel means the kernel of the natural surjection from a graph product to the corresponding direct product. We prove that a graph product kernel of countable groups is special, and a graph product of finite or cyclic groups is virtually cocompact special in the sense of Haglund and Wise. The proof of th…
New bounds on NTK's smallest eigenvalue for arbitrary data without distributional assumptions.
problem Existing bounds on NTK's smallest eigenvalue require distributional assumptions and high-dimensional data.
method Novel application of the hemisphere transform.
result Bounds on NTK's smallest eigenvalue hold with high probability even for constant input dimension.
Study shows Bergman kernel quotient approaches one for punctured surfaces.
problem Analyzing Bergman kernels on punctured Riemann surfaces.
method Examined a punctured Riemann surface with a specific metric and line bundle, calculating quotient of Bergman kernels.
result The quotient of Bergman kernels tends to one as tensor power increases.
New quadrature method using randomly pivoted Cholesky outperforms existing techniques.
problem Efficiently approximating integrals of functions in reproducing kernel Hilbert spaces.
method Nodes drawn by randomly pivoted Cholesky algorithm.
result Randomly pivoted Cholesky quadrature is fast and achieves comparable accuracy to more computationally intensive methods.
Extends Tanimoto kernel to real-valued functions.
problem Measuring similarity between real-valued functions.
method Unified representation of real-valued functions via sets, derived general form of the kernel, explicit feature representation, and smooth approximation.
result General Tanimoto kernel for real-valued functions.
In this paper we propose a family of tractable kernels that is dense in the family of bounded positive semi-definite functions (i.e. can approximate any bounded kernel with arbitrary precision). We start by discussing the case of stationary kernels, and propose a family of spectral kernels that extends existing approac…
Kernelized Q-learning achieves good performance with minimal data.
problem Efficient Q-learning in high-dimensional spaces.
method Kernelized Q-learning framework with effective dimensionality.
result Concrete regret bounds for linear and Gaussian RBF kernels.
A new distributed clustering framework using distributional kernel.
problem Clustering in distributed networks with arbitrary shapes, sizes, and densities.
method Distributed Clustering based on Distributional Kernel (KDC) using similarity of distributions.
result KDC guarantees equivalent clustering outcomes to centralized methods, reduces runtime, and discovers arbitrary clusters.
The paper constructs CR manifolds with arbitrary Levi nondegeneracy.
problem Creating CR manifolds with specific Levi nondegeneracy properties.
method Using CR algebras from su(2) representations, studying iterated Levi forms, and local model equations. result Explicit construction and analysis of homogeneous CR manifolds with arbitrary Levi nondegeneracy.
In this paper we introduce the deep kernelized autoencoder, a neural network model that allows an explicit approximation of (i) the mapping from an input space to an arbitrary, user-specified kernel space and (ii) the back-projection from such a kernel space to input space. The proposed method is based on traditional a…
Extends orbital integral evaluation to center of enveloping algebra.
problem Evaluate semisimple orbital integrals for arbitrary elements in the center of the enveloping algebra.
method Explicit geometric evaluation of Casimir operator to arbitrary elements in the center of the enveloping algebra.
result Extension of orbital integral evaluation to center of enveloping algebra.
KITT uses transformers to quickly recommend kernels for GP models.
problem Kernel selection for high-dimensional GP regression models.
method Transformer-based architecture for generating kernel recommendations.
result KITT selects kernels that perform well on various regression benchmarks.
Conditional kernel mean embeddings are nonparametric models that encode conditional expectations in a reproducing kernel Hilbert space. While they provide a flexible and powerful framework for probabilistic inference, their performance is highly dependent on the choice of kernel and regularization hyperparameters. Neve…
New methods predict drug interactions using drug co-medication patterns and graph matching.
problem Predicting adverse drug reactions from drug combinations.
method Developed novel kernels over drug combinations using support vector machines and graph matching to measure similarities.
result Achieved an AUC of 0.912 on a real-world dataset.
GPs' decisions can vary significantly with different kernels, even if kernels are qualitatively similar.
problem Robustness of GP decisions to kernel choice.
method Solved a constrained optimization problem over a finite-dimensional space to identify changes in GP decisions.
result Decisions made with a GP can be non-robust to kernel choice, even with qualitatively similar kernels.
Generative models of eye gaze help identify viewers from images.
problem Identifying viewers from images based on their eye movements.
method Derived Fisher kernels from generative models of eye gaze to train a discriminative classifier.
result Performance of the classifier improves with better underlying generative models.
New kernel models multi-output Gaussian processes accurately.
problem Challenges in modelling cross-covariances for multiple-output Gaussian processes.
method Replaced Gaussian components with block components of finite bandwidth in spectral mixture kernel.
result First multi-output generalization of spectral mixture kernel that can approximate any stationary multi-output kernel to arbitrary precision.
The study shows inner-product kernels behave similarly to binary kernels in high dimensions.
problem Understanding the behavior of inner-product kernels in high-dimensional data.
method Investigation of eigenspectrum under binary mixture model using random matrix theory.
result The eigenspectrum of inner-product kernels is asymptotically equivalent to binary kernels.
New approach to neural networks by incorporating observation noise and arbitrary prior means.
problem Misspecification on noisy data and limitations of NTK-GP equivalence.
method Introducing a regularizer for observation noise and proposing a shifted network for arbitrary prior means.
result Removes key obstacles to practical Gaussian process modeling in neural networks.
A computational technique borrowed from the physical sciences is introduced to obtain accurate closed-form approximations for the transition probability of arbitrary diffusion processes. Within the path integral framework the same technique allows one to obtain remarkably good approximations of the pricing kernels of f…
A novel algorithm for unbiased graph kernel estimation with subquadratic time complexity.
problem Efficient estimation of graph kernels for large networks.
method Random walk-based algorithm with modulation function parameterized by neural network.
result Higher-quality kernel estimates and efficient scalable learning on larger networks.
The paper analyzes how re-weighting helps in reducing variance in high-dimensional kernel methods under covariate shifts.
problem The challenge of high-dimensional kernel methods under covariate shifts and the role of re-weighting.
method Derives asymptotic expansion of high-dimensional kernels under covariate shifts, analyzes bias-variance decomposition, and characterizes the regularized kernel.
result Re-weighting helps in decreasing variance and can be seen as a data-dependent regularization.
Efficiently approximates kernel mean embeddings using Nyström method.
problem Computational cost of kernel mean embeddings in large-scale settings.
method Nyström method for approximating a small random subset of the dataset.
result Upper bound on approximation error with sufficient subsample size conditions.
t-SNE with Cauchy kernel shows finer cluster structure.
problem Crowding problem in t-SNE visualizations.
method Developed an efficient implementation of t-SNE with a heavy-tailed t-distribution kernel. result Fine cluster structure revealed with ν<1. Study examines boundedness of oscillating singular integrals on specific Lie groups.
problem Investigating boundedness of oscillating singular integrals on Lie groups of polynomial growth.
method Presented kernel criteria in terms of sub-Riemannian structure and Fourier analysis.
result Extended classical oscillating conditions for boundedness of oscillating convolution operators.
A new sequential test for unnormalized densities.
problem Testing unnormalized densities with adaptive stopping.
method Sequential kernelized Stein discrepancy test, using non-uniform Stein kernels.
result Valid test with asymptotic lower bound for growth.
Positive definite kernels and their associated Reproducing Kernel Hilbert Spaces provide a mathematically compelling and practically competitive framework for learning from data. In this paper we take the approximation theory point of view to explore various aspects of smooth kernels related to their inferential proper…
New method uses kernel methods to approximate ground states of quantum Hamiltonians efficiently.
problem Approximating ground states of quantum Hamiltonians using neural networks is computationally expensive.
method Introduces a statistical learning approach using kernel methods to make optimization trivial.
result Ground state properties of arbitrary gapped quantum Hamiltonians can be reached with polynomial resources.
Paper generalizes kernel mean embedding to von Neumann-algebra-valued measures.
problem Analyzing complex multivariate distributions and quantum mechanics.
method Generalizes kernel mean embedding to von Neumann-algebra-valued measures in reproducing kernel Hilbert modules.
result Injectivity and universality of the generalized KME are confirmed.
The use of covariance kernels is ubiquitous in the field of spatial statistics. Kernels allow data to be mapped into high-dimensional feature spaces and can thus extend simple linear additive methods to nonlinear methods with higher order interactions. However, until recently, there has been a strong reliance on a limi…
Paper addresses bias in kernel density estimation under minimal assumptions.
problem Kernel density estimation bias under minimal assumptions.
method Demonstrates the need for a balance between kernel decay and bandwidth eigenvalues, and rigorously derives bias bounds.
result Explicit constants and rigorous derivation of bias bounds under minimal assumptions.
This paper generalizes regularized regression problems in a hyper-reproducing kernel Hilbert space (hyper-RKHS), illustrates its utility for kernel learning and out-of-sample extensions, and proves asymptotic convergence results for the introduced regression models in an approximation theory view. Algorithmically, we c…
The paper improves Stein importance sampling for Markov chain samples.
problem Improving the accuracy of sampling from complex distributions.
method Reproducing Stein kernels approach for post-hoc correction.
result Consistent estimators for target distributions using geometrically ergodic Markov chains.
Accelerates signature kernel computation for sequences.
problem Severe computational bottleneck in computing signature kernel.
method Random Fourier features to accelerate signature kernel computation.
result Uniform approximation guarantees for unbiased estimator with linear computation time.
Similarity learning has received a large amount of interest and is an important tool for many scientific and industrial applications. In this framework, we wish to infer the distance (similarity) between points with respect to an arbitrary distance function d. Here, we formulate the problem as a regression from a fea…
Kernel methods accurately predict Hamiltonian systems from data.
problem Data-driven simulation of Hamiltonian systems.
method Two-step and one-step kernel-based methods for identifying and forecasting Hamiltonian systems.
result Framework achieves accurate, data-efficient predictions across various benchmark systems.
The reproducing kernel Hilbert space (RKHS) embedding of distributions offers a general and flexible framework for testing problems in arbitrary domains and has attracted considerable amount of attention in recent years. To gain insights into their operating characteristics, we study here the statistical performance of…
Paper shows SVMs can interpolate data in various settings.
problem Understanding SVM performance and generalization.
method Flexible analysis framework for proving SVM interpolation in diverse settings.
result Support vector machines can interpolate data in many cases not previously covered.
Boundary effects inflate variance in Gaussian processes, leading to acquisition bias.
problem Boundary-induced acquisition bias in Gaussian processes.
method Traced root cause to geometric mechanism of kernel truncation at domain boundaries.
result Boundary effects create distortion that worsens with dimensionality, affecting acquisition behavior.
Kernel method improves cooperative decision-making among agents.
problem Cooperative multi-agent decision making with contextual information.
method Proposed extsc{Coop-KernelUCB} algorithm for near-optimal per-agent regret.
result Near-optimal bounds on per-agent regret with efficient computation and communication.
Generalizes PCA to maximize any convex function of components.
problem Finding a principal vector that maximizes a convex function of components.
method Gradient ascent algorithm for solving the generalized PCA problem; fixed points of neural networks for kernel version.
result Solutions can be obtained as fixed points of simple neural networks.
Researchers develop flexible kernels for biological sequences with guaranteed reliability.
problem Challenges in applying machine learning to biological sequences, including unreliable methods.
method Theoretical analysis and development of modified kernels to ensure reliability and accuracy.
result Developed kernels that are universal, characteristic, and metrize the space of distributions for biological sequences.
We propose in this work a new family of kernels for variable-length time series. Our work builds upon the vector autoregressive (VAR) model for multivariate stochastic processes: given a multivariate time series x, we consider the likelihood function p_θ(x) of different parameters θin the VAR model as features to descr…