602 citations · 2k across the 59 of their papers we have counts for
26 papers · 1 filter
Nyström Kernel Stein Discrepancy Tests
Florian Kalinke, Zoltán Szabó, Bharath K. Sriperumbudur
Kernel Stein discrepancy (KSD) is among the most popular goodness-of-fit (GoF) measures on general domains with a large number of successful deployments. One of the main applicatio…
Move on Muon : A Hamiltonian probability gradient flow perspective of Muon optimizer
Aratrika Mustafi, Soumya Mukherjee, Bharath K. Sriperumbudur
We develop a gradient flow on the space of probability measures defined on matrix-valued parameters induced by regularized Muon, an analytically smoothed version of the idealized M…
Kernel Single-Index Bandits: Estimation, Inference, and Learning
Sakshi Arya, Satarupa Bhattacharjee, Bharath K. Sriperumbudur
We study contextual bandits with finitely many actions in which the reward of each arm follows a single-index model with an arm-specific index parameter and an unknown nonparametri…
Gaussian Processes and Reproducing Kernel Hilbert Spaces: Connections and Equivalences
Motonobu Kanagawa, Philipp Hennig, Dino Sejdinovic +1
This monograph studies the relations between two approaches using positive definite kernels: probabilistic methods using Gaussian processes, and non-probabilistic methods using rep…
Uniform Kernel Prober
Soumya Mukherjee, Bharath K. Sriperumbudur
The ability to identify useful features or representations of the input data based on training data that achieves low prediction error on test data across multiple prediction tasks…
(De)-regularized Maximum Mean Discrepancy Gradient Flow
Zonghao Chen, Aratrika Mustafi, Pierre Glaser +3
We introduce a (de)-regularization of the Maximum Mean Discrepancy (DrMMD) and its Wasserstein gradient flow. Existing gradient flows that transport samples from source distributio…
Nyström Kernel Stein Discrepancy
Florian Kalinke, Zoltan Szabo, Bharath K. Sriperumbudur
Kernel methods underpin many of the most successful approaches in data science and statistics, and they allow representing probability measures as elements of a reproducing kernel…
Kernel -Greedy for Multi-Armed Bandits with Covariates
Sakshi Arya, Bharath K. Sriperumbudur
We consider the -greedy strategy for the multi-arm bandit with covariates (MABC) problem, where the mean reward functions are assumed to lie in a reproducing kernel Hilbert spac…
Regularized Stein Variational Gradient Flow
Ye He, Krishnakumar Balasubramanian, Bharath K. Sriperumbudur +1
The Stein Variational Gradient Descent (SVGD) algorithm is a deterministic particle method for sampling. However, a mean-field analysis reveals that the gradient flow corresponding…
Statistical Optimality and Computational Efficiency of Nyström Kernel PCA
Nicholas Sterge, Bharath Sriperumbudur
Kernel methods provide an elegant framework for developing nonlinear learning algorithms from simple linear methods. Though these methods have superior empirical performance in sev…
Gaussian Sketching yields a J-L Lemma in RKHS
Samory Kpotufe, Bharath K. Sriperumbudur
The main contribution of the paper is to show that Gaussian sketching of a kernel-Gram matrix yields an operator whose counterpart in an RKHS , is a \em…
Gain with no Pain: Efficient Kernel-PCA by Nyström Sampling
Nicholas Sterge, Bharath Sriperumbudur, Lorenzo Rosasco +1
In this paper, we propose and study a Nyström based approach to efficient large scale kernel principal component analysis (PCA). The latter is a natural nonlinear extension of clas…
On Kernel Derivative Approximation with Random Fourier Features
Zoltan Szabo, Bharath K. Sriperumbudur
Random Fourier features (RFF) represent one of the most popular and wide-spread techniques in machine learning to scale up kernel algorithms. Despite the numerous successful applic…
Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
Motonobu Kanagawa, Philipp Hennig, Dino Sejdinovic +1
This paper is an attempt to bridge the conceptual gaps between researchers working on the two widely used approaches based on positive definite kernels: Bayesian learning or infere…
Characteristic and Universal Tensor Product Kernels
Zoltan Szabo, Bharath K. Sriperumbudur
Maximum mean discrepancy (MMD), also called energy distance or N-distance in statistics and Hilbert-Schmidt independence criterion (HSIC), specifically distance covariance in stati…
Adaptive Clustering Using Kernel Density Estimators
Ingo Steinwart, Bharath K. Sriperumbudur, Philipp Thomann
We derive and analyze a generic, recursive algorithm for estimating all splits in a finite cluster tree as well as the corresponding clusters. We further investigate statistical pr…
Approximate Kernel PCA Using Random Features: Computational vs. Statistical Trade-off
Bharath Sriperumbudur, Nicholas Sterge
Kernel methods are powerful learning methodologies that allow to perform non-linear data analysis. Despite their popularity, they suffer from poor scalability in big data scenarios…
Kernel Mean Embedding of Distributions: A Review and Beyond
Krikamol Muandet, Kenji Fukumizu, Bharath Sriperumbudur +1
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…
Convergence guarantees for kernel-based quadrature rules in misspecified settings
Motonobu Kanagawa, Bharath K. Sriperumbudur, Kenji Fukumizu
Kernel-based quadrature rules are becoming important in machine learning and statistics, as they achieve super- convergence rates in numerical integration, and thus provi…
Kernel Mean Estimation via Spectral Filtering
Krikamol Muandet, Bharath Sriperumbudur, Bernhard Schölkopf
The problem of estimating the kernel mean in a reproducing kernel Hilbert space (RKHS) is central to kernel methods in that it is used by classical approaches (e.g., when centering…
Kernel Mean Shrinkage Estimators
Krikamol Muandet, Bharath Sriperumbudur, Kenji Fukumizu +2
A mean function in a reproducing kernel Hilbert space (RKHS), or a kernel mean, is central to kernel methods in that it is used by many classical algorithms such as kernel principa…
Kernel Mean Estimation and Stein's Effect
Krikamol Muandet, Kenji Fukumizu, Bharath Sriperumbudur +2
A mean function in reproducing kernel Hilbert space, or a kernel mean, is an important part of many applications ranging from kernel principal component analysis to Hilbert-space e…
Universality, Characteristic Kernels and RKHS Embedding of Measures
Bharath K. Sriperumbudur, Kenji Fukumizu, Gert R. G. Lanckriet
A Hilbert space embedding for probability measures has recently been proposed, wherein any probability measure is represented as a mean element in a reproducing kernel Hilbert spac…
Hilbert space embeddings and metrics on probability measures
Bharath K. Sriperumbudur, Arthur Gretton, Kenji Fukumizu +2
A Hilbert space embedding for probability measures has recently been proposed, with applications including dimensionality reduction, homogeneity testing, and independence testing.…