English
Related papers

Related papers: Hyperparameter Selection via Early Stopping for Ba…

200 papers

The numerical solution of differential equations can be formulated as an inference problem to which formal statistical approaches can be applied. However, nonlinear partial differential equations (PDEs) pose substantial challenges from an…

Numerical Analysis · Mathematics 2021-08-26 Junyang Wang , Jon Cockayne , Oksana Chkrebtii , T. J. Sullivan , Chris. J. Oates

We analyze a class of nonlinear partial differential equations (PDEs) defined on $\mathbb{R}^d \times \mathcal{P}_2(\mathbb{R}^d),$ where $\mathcal{P}_2(\mathbb{R}^d)$ is the Wasserstein space of probability measures on $\mathbb{R}^d$ with…

Probability · Mathematics 2015-04-23 Jean-François Chassagneux , Dan Crisan , François Delarue

We consider the problem of performing Bayesian inference for logistic regression using appropriate extensions of the ensemble Kalman filter. Two interacting particle systems are proposed that sample from an approximate posterior and prove…

Machine Learning · Statistics 2024-07-02 Diksha Bhandari , Jakiw Pidstrigach , Sebastian Reich

Deep reinforcement learning excels in numerous large-scale practical applications. However, existing performance analyses ignores the unique characteristics of continuous-time control problems, is unable to directly estimate the…

Machine Learning · Computer Science 2024-03-08 Shuyu Yin , Qixuan Zhou , Fei Wen , Tao Luo

This study proposes the first Bayesian approach for learning high-dimensional linear Bayesian networks. The proposed approach iteratively estimates each element of the topological ordering from backward and its parent using the inverse of a…

Machine Learning · Statistics 2023-11-28 Seyong Hwang , Kyoungjae Lee , Sunmin Oh , Gunwoong Park

In recent years, a considerable amount of work has been devoted to generalizing linear discriminant analysis to overcome its incompetence for high-dimensional classification (Witten & Tibshirani 2011, Cai & Liu 2011, Mai et al. 2012, Fan et…

Methodology · Statistics 2015-01-15 Qing Mai , Hui Zou

High-throughput characterization often requires estimating parameters and model dimension from experimental data of limited quantity and quality. Such data may result in an ill-posed inverse problem, where multiple sets of parameters and…

Quantum Physics · Physics 2026-04-08 Abigail N. Poteshman , Jiwon Yun , Tim H. Taminiau , Giulia Galli

We propose a Bayesian framework for feedback boundary control for hyperbolic balance laws. The method propagates a probability distribution over feedback parameters by using Lyapunov decay estimates as a likelihood. In the linear setting,…

Numerical Analysis · Mathematics 2026-02-03 Markus Bambach , Shaoshuai Chu , Michael Herty , Yunong Lin

This paper introduces a novel Transformed Primal-Dual with variable-metric/preconditioner (TPDv) algorithm, designed to efficiently solve affine constrained optimization problems common in nonlinear partial differential equations (PDEs).…

Numerical Analysis · Mathematics 2023-12-20 Long Chen , Ruchi Guo , Jingrong Wei

We derive an optimal policy for adaptively restarting a randomized algorithm, based on observed features of the run-so-far, so as to minimize the expected time required for the algorithm to successfully terminate. Given a suitable Bayesian…

Machine Learning · Computer Science 2019-02-25 Matthew Streeter

In this paper, we study the problem of early stopping for iterative learning algorithms in a reproducing kernel Hilbert space (RKHS) in the nonparametric regression framework. In particular, we work with the gradient descent and (iterative)…

Machine Learning · Statistics 2024-11-26 Yaroslav Averyanov , Alain Celisse

Complex statistical models are often built by combining multiple submodels, called modules. Here we consider modular inference where the modules contain both parametric and nonparametric components. In such cases, standard Bayesian…

Methodology · Statistics 2026-03-27 Linda S. L. Tan , David J. Nott , David T. Frazier

We show that unconverged stochastic gradient descent can be interpreted as a procedure that samples from a nonparametric variational approximate posterior distribution. This distribution is implicitly defined as the transformation of an…

Machine Learning · Statistics 2015-04-07 Dougal Maclaurin , David Duvenaud , Ryan P. Adams

In this paper, we use an implicit two-derivative deferred correction time discretization approach and combine it with a spatial discretization of the discontinuous Galerkin spectral element method to solve (non-)linear PDEs. The resulting…

Numerical Analysis · Mathematics 2022-07-13 Jonas Zeifang , Jochen Schuetz

We consider Bayesian inverse problems arising in data assimilation for dynamical systems governed by partial and stochastic partial differential equations. The space-time dependent field is inferred jointly with static parameters of the…

Computation · Statistics 2026-03-20 Baptiste Simandoux , Nikolas Kantas , Dan Crisan

The strategy of early stopping is a regularization technique based on choosing a stopping time for an iterative algorithm. Focusing on non-parametric regression in a reproducing kernel Hilbert space, we analyze the early stopping strategy…

Machine Learning · Statistics 2013-06-18 Garvesh Raskutti , Martin J. Wainwright , Bin Yu

Data point selection (DPS) is becoming a critical topic in deep learning due to the ease of acquiring uncurated training data compared to the difficulty of obtaining curated or processed data. Existing approaches to DPS are predominantly…

Machine Learning · Computer Science 2024-11-07 Xinnuo Xu , Minyoung Kim , Royson Lee , Brais Martinez , Timothy Hospedales

We study Tikhonov regularization for certain classes of non-linear ill-posed operator equations in Hilbert space. Emphasis is on the case where the solution smoothness fails to have a finite penalty value, as in the preceding study…

Numerical Analysis · Mathematics 2019-04-04 Bernd Hofmann , Peter Mathé

The discovery of Partial Differential Equations (PDEs) is an essential task for applied science and engineering. However, data-driven discovery of PDEs is generally challenging, primarily stemming from the sensitivity of the discovered…

Machine Learning · Statistics 2024-03-27 Aoxue Chen , Yifan Du , Liyao Mars Gao , Guang Lin

When training large models on limited data, avoiding overfitting is paramount. Common grid search or smarter search methods rely on expensive separate runs for each candidate hyperparameter, while carving out a validation set that reduces…

Machine Learning · Computer Science 2026-04-02 Ethan Harvey , Mikhail Petrov , Michael C. Hughes