English
Related papers

Related papers: Kernel Dynamics under Path Entropy Maximization

200 papers

We derive a closed-form geometric functional for kernel dynamics on finite graphs by applying the Maximum Caliber (MaxCal) variational principle to the spectral transfer function h(lambda) of the graph Laplacian eigenbasis. The main result…

Robotics · Computer Science 2026-04-14 Jnaneshwar Das

We review here {\it Maximum Caliber} (Max Cal), a general variational principle for inferring distributions of paths in dynamical processes and networks. Max Cal is to dynamical trajectories what the principle of {\it Maximum Entropy} (Max…

Statistical Mechanics · Physics 2018-01-17 Purushottam D. Dixit , Jason Wagoner , Corey Weistuch , Steve Pressé , Kingshuk Ghosh , Ken A. Dill

Recent contributions have framed linear system identification as a nonparametric regularized inverse problem. Relying on $\ell_2$-type regularization which accounts for the stability and smoothness of the impulse response to be estimated,…

Systems and Control · Computer Science 2016-09-30 Giulia Prando , Gianluigi Pillonetto , Alessandro Chiuso

Empirical data can often be considered as samples from a set of probability distributions. Kernel methods have emerged as a natural approach for learning to classify these distributions. Although numerous kernels between distributions have…

Machine Learning · Computer Science 2024-12-02 Oleksii Kachaiev , Stefano Recanatesi

We present a unified theoretical framework for temporal knowledge graphs grounded in maximum-entropy principles, differential geometry, and information theory. We prove a unique characterization of scoring functions via the maximum-entropy…

Information Theory · Computer Science 2025-09-16 Ibne Farabi Shihab

The primary hyperparameter in kernel regression (KR) is the choice of kernel. In most theoretical studies of KR, one assumes the kernel is fixed before seeing the training data. Under this assumption, it is known that the optimal kernel is…

Machine Learning · Computer Science 2022-09-28 James B. Simon

A new nonparametric approach for system identification has been recently proposed where the impulse response is seen as the realization of a zero--mean Gaussian process whose covariance, the so--called stable spline kernel, guarantees that…

Statistics Theory · Mathematics 2016-11-18 Francesca Paola Carli

We investigate the mathematical foundations of neural networks in the infinite-width regime through the Neural Tangent Kernel (NTK). We propose the NTK-Eigenvalue-Controlled Residual Network (NTK-ECRN), an architecture integrating Fourier…

Kernel methods form a theoretically-grounded, powerful and versatile framework to solve nonlinear problems in signal processing and machine learning. The standard approach relies on the \emph{kernel trick} to perform pairwise evaluations of…

Machine Learning · Computer Science 2020-01-03 Kan Li , Jose C. Principe

A new nonparametric approach for system identification has been recently proposed where the impulse response is modeled as the realization of a zero-mean Gaussian process whose covariance (kernel) has to be estimated from data. In this…

Optimization and Control · Mathematics 2016-11-17 Francesca Paola Carli , Tianshi Chen , Lennart Ljung

The notion of reproducing kernel Hilbert space (RKHS) has emerged in system identification during the past decade. In the resulting framework, the impulse response estimation problem is formulated as a regularized optimization defined on an…

Systems and Control · Electrical Eng. & Systems 2022-04-19 Mohammad Khosravi , Roy S. Smith

Expressiveness and generalization of deep models was recently addressed via the connection between neural networks (NNs) and kernel learning, where first-order dynamics of NN during a gradient-descent (GD) optimization were related to…

Machine Learning · Computer Science 2020-04-21 Dmitry Kopitkov , Vadim Indelman

The Neural Tangent Kernel (NTK) framework has provided deep insights into the training dynamics of neural networks under gradient flow. However, it relies on the assumption that the network is differentiable with respect to its parameters,…

Machine Learning · Computer Science 2025-09-17 Sriram Nagaraj , Vishakh Hari

We investigate the maximum caliber variational principle as an inference algorithm used to predict dynamical properties of complex nonequilibrium, stationary, statistical systems in the presence of incomplete information. Specifically, we…

Statistical Mechanics · Physics 2016-12-28 Carlo Cafaro , Sean Alan Ali

Tabular foundation models like TabPFN and TabICL achieve state-of-the-art performance through in-context learning, yet their architectures remain fundamentally opaque. We introduce KernelICL, a framework to enhance tabular foundation models…

Machine Learning · Computer Science 2026-02-03 Ratmir Miftachov , Bruno Charron , Simon Valentin

The Neural Tangent Kernel (NTK) offers a powerful tool to study the functional dynamics of neural networks. In the so-called lazy, or kernel regime, the NTK remains static during training and the network function is linear in the static…

Machine Learning · Computer Science 2025-07-28 Yuzhi Liu , Zixuan Chen , Zirui Zhang , Yufei Liu , Giulia Lanzillotta

State-of-the-art neural networks are heavily over-parameterized, making the optimization algorithm a crucial ingredient for learning predictive models with good generalization properties. A recent line of work has shown that in a certain…

Machine Learning · Statistics 2019-11-01 Alberto Bietti , Julien Mairal

For each rank metric code $\mathcal{C}\subseteq \mathbb{K}^{m\times n}$, we associate a translation structure, the kernel of which is shown to be invariant with respect to the equivalence on rank metric codes. When $\mathcal{C}$ is…

Combinatorics · Mathematics 2017-04-20 Guglielmo Lunardon , Rocco Trombetti , Yue Zhou

Neural tangent kernels (NTKs) provide a theoretical regime to analyze the learning and generalization behavior of over-parametrized neural networks. For a supervised learning task, the association between the eigenvectors of the NTK kernel…

Machine Learning · Computer Science 2023-10-18 Shervin Khalafi , Saurabh Sihag , Alejandro Ribeiro

MaxCal is a variational principle that can be used to infer distributions of paths in the phase space of dynamical systems. It has been successfully applied to different areas of classical physics, in particular statistical mechanics in and…

Statistical Mechanics · Physics 2018-07-02 Ignacio J. General
‹ Prev 1 2 3 10 Next ›