Adapts manifold structure for better clustering performance.
problem Lack of consideration for local manifold structure in existing multiple kernel k-means methods.
method Adopts manifold adaptive kernel to integrate local manifold structure of kernels.
result Proposed method outperforms state-of-the-art methods.
New classifier combines locally linear kernels for fast and accurate non-linear classification.
problem Developing a fast and accurate non-linear classifier.
method Combines locally linear classifiers using a ℓ1 Multiple Kernel Learning (MKL) problem with scalable MKL training for streaming kernels. result The resulting classifier achieves high accuracy with fast inference time.
New quantum kernels avoid overfitting by combining local and global components.
problem Exponential concentration in quantum kernels leads to overfitting.
method Local-global quantum kernels combining small subsystem and full-system measurements.
result Demonstrated benign overfitting in local-global quantum kernels.
New kernels capture both local and non-local interactions efficiently.
problem Designing kernels that capture both local and non-local interactions while remaining computationally tractable.
method Spectral truncation kernels based on C∗-algebra. result Spectral truncation kernels induce interactions across the data function domain and reduce computational cost.
The paper studies local heat kernel properties on smooth manifolds.
problem Understanding heat kernel properties in open convex sets of smooth Riemannian manifolds.
method Utilizes path integral formulation to investigate properties like uniqueness, symmetry, and asymptotics.
result Uniqueness and symmetry of Seeley-DeWitt coefficients are established.
Unified analysis of kernel-based and locally adaptive bandit optimization methods.
problem Performance of bandit optimization algorithms in RKHS functions.
method Investigates the relationship between kernel regularity and algorithmic performance, characterizing spectral properties of various kernels.
result Unified framework for analyzing kernel-based and locally adaptive bandit algorithms, deriving explicit regret bounds.
Localized Multiple Kernel Learning improves anomaly detection performance.
problem Anomaly detection in one-class classification tasks.
method Localized Multiple Kernel Learning (LMKAD) for One-class Classification (OCC).
result LMKAD achieves significantly better Gmean scores with fewer support vectors.
Multiple Kernel Learning, or MKL, extends (kernelized) SVM by attempting to learn not only a classifier/regressor but also the best kernel for the training task, usually from a combination of existing kernel functions. Most MKL methods seek the combined kernel that performs best over every training example, sacrificing…
Gaussian process regression loses locality in high dimensions, affecting molecular energy surface fitting.
problem Loss of locality in high-dimensional Gaussian process regression.
method Analysis of Matern family kernels and multi-zeta basis functions.
result The property of locality disappears in high dimensions, impacting regression quality.
This paper improves neural tangent kernels for better generalization and local elasticity.
problem Performance gap between neural tangent kernels and real-world neural networks.
method Introduces label-aware kernels using Hoeffding decomposition.
result Models trained with proposed kernels simulate NNs better in terms of generalization and local elasticity.
Improved kernel ridge regression for large datasets using weighted random binning.
problem Efficiently approximating kernel matrices for large-scale datasets.
method Introduced weighted random binning features for locality sensitive hashing.
result Weighted random binning features generate Gaussian processes of any desired smoothness.
A new multi-kernel RBFNN design improves performance and speed.
problem Improving the performance and speed of RBFNNs.
method Proposes a novel multi-kernel RBFNN where each base kernel has its own weight.
result Better performance gains including faster convergence, better local minima, and resilience against poor local minima.
Generalizes machine learning models using localization kernels and local means.
problem Understanding and unifying diverse machine learning models.
method Formal definition of localization method through localization kernels and local means.
result Unified theoretical lens and new methodological tools for designing flexible learning systems.
A new convolutional spectral kernel network learns hierarchical and local features.
problem Lack of deep learning in non-stationary spectral kernels.
method Introduces convolutional filters and deep architectures into non-stationary spectral kernels, derives generalization error bounds, and introduces regularizers.
result Validated the effectiveness of the convolutional spectral kernel network on real-world datasets.
Let X be a hermitian manifold and let L^k be a high power of a hermitian line bundle over X. Local versions of Demailly's holomorphic Morse inequalities are presented - after integration they yield the usual inequalities. The local weak inequalities hold on any hermitian manifold X, regardless of compactness and comple…
Unified framework combines trace-induced quantum kernels for improved machine learning models.
problem Improving performance of quantum machine learning models using trace-induced kernels.
method Developed a unified framework combining various trace-induced quantum kernels, including global fidelity and local projected kernels, as Lego kernels.
result Local projected kernels can achieve comparable performance to global fidelity kernels with fewer quantum resources.
MIK improves t-SNE's local structure preservation in biological sequence data.
problem Efficiently preserving local structure in high-dimensional biological sequence data.
method Modified Isolation Kernel (MIK) using adaptive density estimation.
result MIK preserves local and global structure better than Gaussian and isolation kernels.
New MMD statistic detects differences between locally low-dimensional distributions.
problem Detecting differences between two locally low-dimensional distributions.
method Anisotropic kernel-based Maximum Mean Discrepancy (MMD) statistic.
result Consistent test under mild assumptions, with finite-sample lower bound of testing power.
Accelerates GPR with localized kernels for faster performance.
problem Speeding up Gaussian process regression.
method Localization kernels applied at each data point to down-weight distant points, leading to a sparsified Gram matrix.
result Significant speedups with competitive performance compared to other methods.
Improved guarantees for misspecified kernelized bandit optimization.
problem Misspecification in kernelized bandit optimization.
method Localization and domain splitting techniques.
result Logarithmic or polylogarithmic growth of misspecification amplification.
Invariance to nuisance transformations is one of the desirable properties of effective representations. We consider transformations that form a \emph{group} and propose an approach based on kernel methods to derive local group invariant representations. Locality is achieved by defining a suitable probability distributi…
We consider the heat kernel (and the zeta function) associated with Laplace type operators acting on a general irreducible rank 1 locally symmetric space X. The set of Minakshisundaram- Pleijel coefficients {A_k(X)}_{k=0}^{\infty} in the short-time asymptotic expansion of the heat kernel is calculated explicitly.
Study Bergman kernels on complex hyperbolic cusps, generalizing previous results.
problem Localization of Bergman kernels on Kähler manifolds with complex hyperbolic cusps.
method Revisiting Tian's peak section method, applying to Kähler-Einstein metrics and quotients of complex balls.
result Partial localization result for Poincaré type cusps.
The paper proves deep ReLU networks avoid spurious local minima in NTK regime.
problem The existence of spurious local minima in deep ReLU neural networks.
method Theoretical proof under Neural Tangent Kernel regime.
result Deep ReLU networks do not lie in spurious local minima in NTK regime.
Graph kernel uses Ricci curvature for comparison.
problem Graph comparison without node attributes.
method Edge curvature distribution for graph kernel.
result Graphs can be compared using topology alone.
Paper introduces new neural network models and theories.
problem Understanding neural networks beyond over-parameterized regime.
method Develops two exact models and a novel representor theory.
result Provides insights into neural network training and kernel evolution.
The paper analyzes early stopping for boosting algorithms using localized Gaussian complexity.
problem Understanding the performance of early stopping in kernel boosting algorithms.
method Direct connection between stopped iterate performance and localized Gaussian complexity of function classes.
result Optimal stopping rules derived for various kernel classes, showing correspondence with practice.
We derive an upper bound on the local Rademacher complexity of ℓp-norm multiple kernel learning, which yields a tighter excess risk bound than global approaches. Previous local approaches aimed at analyzed the case p=1 only while our analysis covers all cases 1≤p≤∞, assuming the different feature …
Flexible Kernels for Protein Property Prediction
problem Predicting protein properties from sparse experimental data
method Sequence kernels using evolutionary substitution matrices and local linearity
result Data-efficient models of protein property landscapes
Needlets have been recognized as state-of-the-art tools to tackle spherical data, due to their excellent localization properties in both spacial and frequency domains. This paper considers developing kernel methods associated with the needlet kernel for nonparametric regression problems whose predictor variables are de…
The massive amount of available data potentially used to discover patters in machine learning is a challenge for kernel based algorithms with respect to runtime and storage capacities. Local approaches might help to relieve these issues. From a statistical point of view local approaches allow additionally to deal with …
A new algorithm combines SVGD with local kernels for efficient inference in continuous graph models.
problem Efficient inference in high-dimensional continuous graphical models.
method Stein variational gradient descent extended with local kernels.
result Local kernels improve approximation and enable distributed inference.
The paper studies heat kernel asymptotics and proves Morse inequalities.
problem Analyzing the asymptotic behavior of heat kernels near critical points.
method Localization and scaling techniques in semi-classical analysis.
result The heat kernel near critical points is approximated by harmonic oscillator kernels, leading to Morse inequalities.
Heat kernels exist and are Hölder for rough metrics on smooth manifolds.
problem Existence and regularity of heat kernels on rough metrics.
method Local parabolic Harnack estimates for weak solutions in weighted Sobolev spaces.
result Globally continuous heat kernels are Hölder continuous locally.
LMKL-Net uses deep neural networks to solve localized multiple kernel learning faster and more efficiently.
problem Localized multiple kernel learning (LMKL) optimization problem.
method LMKL-Net employs a feedforward deep neural network with attentional networks and multilayer perceptrons to learn kernel combination weights and multiclass classifiers.
result LMKL-Net outperforms state-of-the-art MKL solvers in accuracy and is trained much faster and with less memory.
Paper proposes a robust LPR method using similarity kernels.
problem Outliers and high-leverage points affect traditional LPR's accuracy.
method Integrates predictor and response variables in weighting mechanism using a conditional density kernel.
result Lower empirical bias compared to iterative robust LOWESS.
In this paper we consider a punctured Riemann surface endowed with a Hermitian metric which equals the Poincaré metric near the punctures and a holomorphic line bundle which polarizes the metric. We show that the Bergman kernel can be localized around the singularities and its local model is the Bergman kernel of the p…
Estimates path-valued data using signature metrics and local kernels.
problem Nonparametric regression and classification for path-valued data.
method Combines signature transform and local kernel regression.
result Establishes convergence bounds and demonstrates competitive accuracy.
Unified framework for global and local two-sample conditional distribution testing.
problem Testing equality of two conditional distributions.
method Distance and kernel methods, conditional U-statistics, local bootstrap.
result Developed reliable global and local tests.
This paper consists of two parts. In the first part we show that in odd dimension, as well as in even dimension below the critical weight (i.e. half the dimension), the logarithmic singularities of Schwartz kernels and Green kernels of conformal invariant pseudodifferential operators are linear combinations of Weyl con…
Proposes DR-ME test for interpretable distributional treatment effects.
problem Detects invisible differences in treatment effects on distributional outcomes.
method Semiparametrically efficient finite-location test using kernel witnesses and orthogonal features.
result DR-ME reveals causal-discrepancy coordinates and has noncentral chi-square local power.
Classifies vector fields in the kernel of a 1-form, up to equivalence.
problem Classifying vector fields in the kernel of a 1-form.
method Equivalence relation, local models, transversal unfoldings.
result Provides a list of local models and transversal unfoldings for vector fields.
New method for spectral and Bergman kernels under local spectral gap condition.
problem Analyzing spectral and Bergman kernels for complex manifolds.
method Developed a new scaling method to study spectral and Bergman kernels.
result Established pointwise asymptotics of spectral and Bergman kernels.
Locality helps in learning from high-dimensional data.
problem Understanding how convolutional neural networks learn from high-dimensional data.
method Teacher-student framework for kernel regression with convolutional kernels.
result Locality is key to determining the learning curve exponent in high-dimensional data.
Researchers derived heat kernel expansions for non-compact spaces using Witten deformation.
problem Heat kernel expansions on non-compact spaces, especially for Witten Laplacians.
method Introduced parabolic distance and used it to derive asymptotic expansions.
result Derived an asymptotic expansion of trace of heat kernel for small-time t. New method improves Gaussian kernel approximations for high-frequency data.
problem Limited scalability of kernel-based models to large data sets.
method Local random feature approximations using Maclaurin expansions and polynomial sketches.
result Significant improvement in kernel approximations and downstream performance for high-frequency data.
Metrics specifying distances between data points can be learned in a discriminative manner or from generative models. In this paper, we show how to unify generative and discriminative learning of metrics via a kernel learning framework. Specifically, we learn local metrics optimized from parametric generative models. T…
Study local convergence of GDA for training GANs with kernel-based discriminators.
problem Analyzing the local dynamics of GDA for GANs with kernel-based discriminators.
method Linearization of a non-linear dynamical system, under an isolated points model assumption.
result Showed phase transitions indicating convergence, oscillation, or divergence of GDA.