English
Related papers

Related papers: Sliced Kernelized Stein Discrepancy

200 papers

The Stein Variational Gradient Descent method is a variational inference method in statistics that has recently received a lot of attention. The method provides a deterministic approximation of the target distribution, by introducing a…

Analysis of PDEs · Mathematics 2024-12-16 José A. Carrillo , Jakub Skrzeczkowski , Jethro Warnett

While theoretically appealing, the application of the Wasserstein distance to large-scale machine learning problems has been hampered by its prohibitive computational cost. The sliced Wasserstein distance and its variants improve the…

Machine Learning · Computer Science 2022-03-18 Xiongjie Chen , Yongxin Yang , Yunpeng Li

Stochastic gradient descent (SGD) now acts as a fundamental part of optimization in current machine learning. Meanwhile, deep learning architectures have shown outstanding performance in a wide range of fields, such as natural language…

Machine Learning · Computer Science 2026-01-27 Zhao Song , Song Yue

This paper provides a unifying view of optimal kernel hypothesis testing across the MMD two-sample, HSIC independence, and KSD goodness-of-fit frameworks. Minimax optimal separation rates in the kernel and $L^2$ metrics are presented, with…

Machine Learning · Statistics 2025-12-30 Antonin Schrab

We present a convergence rate analysis for biased stochastic gradient descent (SGD), where individual gradient updates are corrupted by computation errors. We develop stochastic quadratic constraints to formulate a small linear matrix…

Optimization and Control · Mathematics 2020-03-31 Bin Hu , Peter Seiler , Laurent Lessard

Semi-implicit variational inference (SIVI) extends traditional variational families with semi-implicit distributions defined in a hierarchical manner. Due to the intractable densities of semi-implicit distributions, classical SIVI often…

Machine Learning · Statistics 2024-05-30 Ziheng Cheng , Longlin Yu , Tianyu Xie , Shiyue Zhang , Cheng Zhang

We propose a nonparametric statistical test for goodness-of-fit: given a set of samples, the test determines how likely it is that these were generated from a target density function. The measure of goodness-of-fit is a divergence…

Machine Learning · Statistics 2016-09-28 Kacper Chwialkowski , Heiko Strathmann , Arthur Gretton

In contrast with Mercer kernel-based approaches as used e.g., in Kernel Principal Component Analysis (KPCA), it was previously shown that Singular Value Decomposition (SVD) inherently relates to asymmetric kernels and Asymmetric Kernel…

Machine Learning · Computer Science 2025-03-11 Qinghua Tao , Francesco Tonin , Alex Lambert , Yingyi Chen , Panagiotis Patrinos , Johan A. K. Suykens

Stochastic Gradient Descent (SGD) has become the method of choice for solving a broad range of machine learning problems. However, some of its learning properties are still not fully understood. We consider least squares learning in…

Machine Learning · Statistics 2020-06-22 Nicole Mücke , Enrico Reiss

Real-world datasets are often of high dimension and effected by the curse of dimensionality. This hinders their comprehensibility and interpretability. To reduce the complexity feature selection aims to identify features that are crucial to…

Machine Learning · Computer Science 2023-04-18 Maximilian Stubbemann , Tobias Hille , Tom Hanika

In large-scale regression problems, random Fourier features (RFFs) have significantly enhanced the computational scalability and flexibility of Gaussian processes (GPs) by defining kernels through their spectral density, from which a finite…

Machine Learning · Computer Science 2024-06-05 Houston Warren , Rafael Oliveira , Fabio Ramos

Low-precision training has become crucial for reducing the computational and memory costs of large-scale deep learning. However, quantizing gradients introduces magnitude shrinkage, which can change how stochastic gradient descent (SGD)…

Machine Learning · Computer Science 2026-01-09 Vincent-Daniel Yun

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…

Machine Learning · Statistics 2017-09-26 Krishnakumar Balasubramanian , Tong Li , Ming Yuan

We present a geometric formulation of the Multiple Kernel Learning (MKL) problem. To do so, we reinterpret the problem of learning kernel weights as searching for a kernel that maximizes the minimum (kernel) distance between two convex…

Machine Learning · Computer Science 2014-03-18 John Moeller , Parasaran Raman , Avishek Saha , Suresh Venkatasubramanian

For a certain scaling of the initialization of stochastic gradient descent (SGD), wide neural networks (NN) have been shown to be well approximated by reproducing kernel Hilbert space (RKHS) methods. Recent empirical work showed that, for…

Machine Learning · Statistics 2022-01-12 Behrooz Ghorbani , Song Mei , Theodor Misiakiewicz , Andrea Montanari

In the statistical literature, as well as in artificial intelligence and machine learning, measures of discrepancy between two probability distributions are largely used to develop measures of goodness-of-fit. We concentrate on quadratic…

Methodology · Statistics 2025-10-01 Marianthi Markatou , Giovanni Saraceno

In multi-goal Reinforcement Learning, an agent can share experience between related training tasks, resulting in better generalization for new tasks at test time. However, when the goal space has discontinuities and the reward is sparse, a…

Machine Learning · Computer Science 2023-05-03 Nicolas Castanet , Sylvain Lamprier , Olivier Sigaud

Machine learning models deployed in the wild can be challenged by out-of-distribution (OOD) data from unknown classes. Recent advances in OOD detection rely on distance measures to distinguish samples that are relatively far away from the…

Machine Learning · Computer Science 2023-12-25 Soumya Suvra Ghosal , Yiyou Sun , Yixuan Li

The non-asymptotic analysis of Stochastic Gradient Descent (SGD) typically yields bounds that decompose into a bias term and a variance term. In this work, we focus on the bias component and study the extent to which SGD can match the…

Optimization and Control · Mathematics 2026-02-02 Daniel Cortild , Lucas Ketels , Juan Peypouquet , Guillaume Garrigos

Ordinary differential equation (ODE) is widely used in modeling biological and physical processes in science. In this article, we propose a new reproducing kernel-based approach for estimation and inference of ODE given noisy observations.…

Methodology · Statistics 2021-10-26 Xiaowu Dai , Lexin Li