Infinite-Task Learning uses RKHSs to learn functions over hyperparameter space.
problem Learning a continuum of tasks with various loss functions.
method Utilizes operator-valued kernels and vector-valued RKHSs to control hyperparameters and constraints.
result Generalization guarantees and practical applications in classification, regression, and estimation.
Paper develops metrics for random dynamical systems using vector-valued RKHSs.
problem Creating metrics for random nonlinear dynamical systems.
method Develops metrics on random dynamical systems using Perron-Frobenius operators in vector-valued reproducing kernel Hilbert spaces (vvRKHSs). Uses operator-valued kernels and time-wise independence criteria.
result Extends existing metrics for deterministic systems and introduces kernel maximal mean discrepancy for random processes.
Paper develops a duality approach for robust loss functions in infinite-dimensional RKHSs.
problem Robustness issues in infinite-dimensional RKHSs with operator-valued kernels.
method Develops a duality approach to solve OVK machines for various loss functions.
result Empirical improvements and theoretical stability analysis for robust structured data applications.
Kernel Autoencoder (KAE) encodes any data type using RKHSs.
problem Representing any data type in a compact form.
method KAE uses mappings from vv-RKHSs to minimize reconstruction error.
result KAE can autoencode any kind of data by choosing X as a RKHS.
New approach to supervised learning in RKHS and vvRKHS using C∗-algebras.
problem Traditional supervised learning in RKHS and vvRKHS.
method Generalizing supervised learning to RKHM using C∗-algebras. result Constructing RKHMs with enhanced representation power.
New mathematical foundations for stable RKHSs improve system identification.
problem Improving stability tests and modeling of impulse responses.
method Providing new structural properties and stability conditions for stable RKHSs.
result Any stable kernel admits feature maps induced by orthogonal eigenvectors in l2.
Develops a framework for learning nonlinear operators using Mercer kernels.
problem Learning nonlinear operators between infinite-dimensional spaces.
method Stochastic approximation framework with Mercer operator-valued kernels.
result Establishes dimension-free polynomial convergence rates for nonlinear operator learning.
New learning rates for embeddings in RKHSs, even when the target is not Hilbert-Schmidt.
problem Applying conditional mean embeddings to complex ML/RL settings with infinite-dimensional RKHSs.
method Developed novel learning rates using interpolation theory for RKHSs, derived explicit adaptive rates for sample estimator.
result Achieved uniform convergence rates in the output RKHS for certain parameter regimes.
Unified framework for hard affine SDP constraints in vRKHSs.
problem Incorporating shape constraints into predictive models for rich function classes.
method Unified convex optimization framework using second-order cone tightening.
result Unified and modular approach for handling multiple shape constraints.
New bound explains why high-rank neural nets generalize well.
problem Understanding why high-rank neural networks generalize well.
method Using Koopman operators, group representations, and RKHSs, a new Rademacher complexity bound is derived.
result Derives a bound for a wider range of realistic models.
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)…
Abstract: Generalizes multisymplectic forms to vector-valued versions.
problem Generalizing multisymplectic forms to vector-valued versions.
method Obtained a standard local presentation and proved an entropy inequality for partial compositions.
result Vector-valued multisymplectic forms form a non-unital operad.
The paper defines functions that induce bounded composition operators on RKHSs with analytic positive definite functions.
problem Characterizing functions that induce bounded composition operators on RKHSs.
method Intrinsic properties of RKHSs and asymptotic properties of orthogonal polynomials.
result Only affine transforms can induce bounded composition operators in a large class of RKHSs.
Improved bounds and algorithms for vector-valued learning using unlabeled data.
problem Vector-valued learning with improved bounds and algorithms.
method Local Rademacher complexity and Laplacian regularization.
result Significantly improved convergence rates and better performance.
Estimates nonlinear Hawkes processes using RKHSs with ReLU rectification.
problem Nonlinear multivariate Hawkes processes with complex interaction functions.
method Nonparametric estimation using RKHSs with approximations for ReLU and integral operators.
result Proposes an estimation method with bounds on approximation errors.
The paper extends consistency results for sequential design strategies to vector-valued Gaussian processes.
problem Estimating excursion sets of vector-valued Gaussian processes.
method Clarifying the connection between continuous Gaussian processes and Gaussian measures in Banach spaces, extending concepts and properties from scalar-valued settings to vector-valued settings.
result Consistency results for sequential design strategies can be applied to vector-valued Gaussian processes.
We discuss sharp Sobolev inequalities for vector valued maps.
Motivated by multi-task machine learning with Banach spaces, we propose the notion of vector-valued reproducing kernel Banach spaces (RKBS). Basic properties of the spaces and the associated reproducing kernels are investigated. We also present feature map constructions and several concrete examples of vector-valued RK…
Optimal rates for vector-valued regression on various norms.
problem Optimal rates for vector-valued ridge regression on continuous norms.
method Combining standard capacity assumptions with tensor product constructions of vector-valued interpolation spaces.
result Optimal rates for vector-valued ridge regression, independent of output space dimension.
Proposes a new log-rank test using RKHSs for robust two-sample analysis.
problem Two-sample problem in right-censored data.
method Test statistic based on supremum of RKHS-weighted log-rank tests.
result Proposed test is omnibus for a specific family of RKHSs.
SL(n) covariant valuations on Orlicz spaces are represented and characterized.
problem Representing SL(n) covariant valuations on Orlicz spaces.
method Representation theorem established for continuous, SL(n) covariant vector-valued valuations.
result Unique characterization of SL(n) covariant valuations as moment vectors.
Generative model uses ODEs and RKHSs for measure matching.
problem Minimum divergence generative modeling and sampling.
method Diffeomorphic matching and image registration principles applied to ODEs and RKHSs.
result Theoretical error bounds and extensive numerical experiments demonstrate the method's properties and applicability.
Boosting framework for vector-valued prediction with geometric stability.
problem Lack of a general theoretical understanding of aggregation for structured prediction.
method Identifies (α,β)-stability property and proposes a boosting framework based on exponential reweighting and geometric-median aggregation. result Obtains exponential decay of empirical divergence error under weak learner condition and (α,β)-stability. Study confirms learning rates for vector-valued spectral algorithms, proving consistency.
problem Theoretical confirmation of learning rates for vector-valued spectral algorithms.
method Rigorous analysis of learning rates for various vector-valued spectral algorithms, including kernel ridge regression and gradient descent.
result Upper and lower bounds on learning rates for vector-valued spectral algorithms, proving minimax optimality in various scenarios.
The space of vector-valued forms on any manifold is a graded Lie algebra with respect to the Frolicher-Nijenhuis bracket. In this paper we consider multiplicative vector-valued forms on Lie groupoids and show that they naturally form a graded Lie subalgebra. Along the way, we discuss various examples and different char…
Enhanced kernel ridgeless regression improves performance with LAB RBF kernels.
problem Lack of flexibility in kernel ridgeless regression.
method Locally-Adaptive-Bandwidths (LAB) RBF kernels and kernel learning techniques.
result Functions learned from LAB RBF kernels belong to an integral space of RKHSs, demonstrating robust generalization.
The paper shows vector-valued risk measures ignore dependence structures.
problem Defining capital allocation rules for random vectors with dependence.
method Defined vector-valued risk measures by axioms and showed their properties.
result Vector-valued risk measures ignore dependence structures, unlike set-valued measures.
This study improves graph signal denoising for vector-valued data with non-convex penalties.
problem Denoising piecewise smooth graph signals with varying smoothness levels.
method Extended graph trend filtering with non-convex penalties and ADMM algorithm.
result Non-convex penalties outperform convex ones in recovery performance.
The paper proposes methods to find a shared active subspace for multivariate vector-valued functions.
problem Minimizing the deviation between function evaluations in the original and reconstructed spaces.
method Manipulating gradients or SPD matrices to identify a shared structure.
result Summing SPD matrices often identifies the best shared active subspace.
Optimal transport for vector Gaussian mixtures improves efficiency and structure preservation.
problem Optimal mass transport for vector-valued Gaussian mixtures.
method Vectorizing Gaussian mixture models and studying optimal mass transport problems.
result Computational efficiency and structure preservation in optimal mass transport.
No arbitrage holds if a Pareto solution exists for vector-valued utility maximization.
problem Existence of no arbitrage in markets with transaction costs and multiple assets.
method Prove no arbitrage condition equivalent to Pareto solution for vector-valued utility maximization.
result A consistent price process can be constructed from the Pareto maximizer.
Learning from examples is one of the key problems in science and engineering. It deals with function reconstruction from a finite set of direct and noisy samples. Regularization in reproducing kernel Hilbert spaces (RKHSs) is widely used to solve this task and includes powerful estimators such as regularization network…
We present a framework to derive risk bounds for vector-valued learning with a broad class of feature maps and loss functions. Multi-task learning and one-vs-all multi-category learning are treated as examples. We discuss in detail vector-valued functions with one hidden layer, and demonstrate that the conditions under…
New algorithms improve GP inference without approximations, achieving better results.
problem Inexact stochastic optimization methods in Gaussian Processes leading to biased results.
method Exact stochastic inference for GPs with finite dimensional RKHS, extending to infinite dimensions.
result Achieves better experimental results than existing methods in constrained resource settings.
Study improves self-normalized bounds for vector-valued processes beyond sub-Gaussianity.
problem Limited understanding of self-normalized concentration for vector-valued processes outside sub-Gaussian frameworks.
method Developed concentration inequalities for self-normalized processes with light tails (e.g., Bennett, Bernstein bounds) for vector-valued data.
result Provided new insights and bounds for self-normalized processes with non-sub-Gaussian distributions.
Optimizes reward learning design for complex tasks using nonparametric methods.
problem Challenges in specifying reward functions for complex tasks.
method Models rewards and policies as nonparametric functions in RKHSs, derives risk bounds, and optimizes query design.
result Derives non-asymptotic excess risk bounds and finite sample statistical rates for reward learning.
We approximate derivatives of functions on manifolds by embedding them and applying vector-valued operators.
problem Derivatives of manifold-valued functions are harder to approximate than vector-valued functions.
method Embed the manifold into a higher space, approximate the derivative of the vector-valued function, and project back.
result We provide error bounds for the approximation of manifold-valued function derivatives.
Paper introduces vector-valued variation spaces for multi-output neural networks.
problem Understanding and optimizing multi-output neural networks.
method Development of vector-valued variation spaces and representer theorem.
result Novel bounds for layer widths in deep networks and a convex optimization method for compression.
Framework extends neural operators to handle functions outside training set.
problem Robust handling of functions beyond the training set.
method Kernel approximation techniques and Reproducing Kernel Hilbert Spaces (RKHSs) theory.
result Theoretical framework and empirical validation for reliable function extension.
Paper analyzes error bounds for learning with vector-valued RF, improving existing analyses.
problem Learning with vector-valued random features in infinite-dimensional settings.
method Direct analysis of risk functional, avoiding random matrix theory.
result Strong consistency and minimax optimal convergence rates established.
Randomized algorithm solves vector-valued regression problems with low-rank operators.
problem Vector-valued regression problems involving infinite-dimensional spaces.
method Randomized Reduced Rank Regression (R4) using Gaussian sketching for optimization.
result R4 estimators are efficient and accurate, with empirical risk close to optimal.
We study compressing empirical measures in finite RKHSs using convex optimization.
problem Efficiently approximating empirical measures in high-dimensional spaces.
method Convex optimization and lower bounds on ball size.
result High probability lower bounds on ball size under various conditions.
Paper proves non-equivalence of RKHS stability and kernel absolute summability.
problem Equivalence of RKHS stability and kernel absolute summability.
method Analyzes Reproducing Kernel Hilbert spaces and positive semidefinite kernels.
result Stable RKHSs can be induced by non-absolutely summable kernels.
In this paper we find solutions uε to a certain class of vector-valued parabolic Allen-Cahn equation that as ε→0 develops as interface a given triod evolving under curve shortening flow.
Develops vector-valued RKBS for neural networks and operators.
problem Understanding function spaces of Rd-valued neural networks and neural operators. method Defines and constructs vector-valued RKBS (vv-RKBS) without restrictive assumptions.
result Establishes Representer Theorem for neural architectures.
Introduces a metric on vector-valued one-forms for functional data analysis.
problem Metric on vector-valued one-forms for functional data analysis.
method Diffeomorphism-invariant Riemannian metric calculation and geodesic equations.
result Geodesically and metrically incomplete space with specific curvature properties.
Paper develops a theory for Patterson-Sullivan measures in higher rank symmetric spaces.
problem Establishing existence and uniqueness of Patterson-Sullivan measures in higher rank symmetric spaces.
method Develops theory for vector-valued horofunction boundaries and shadows.
result Proves existence and uniqueness of Patterson-Sullivan measures for transverse groups.
New method transfers emotions in facial images.
problem Transforming facial images to different emotions.
method Infinite task learning and vector-valued reproducing kernel Hilbert spaces.
result Achieves low reconstruction cost and high emotion classification accuracy.