English
Related papers

Related papers: On the implicit regularization of Langevin dynamic…

200 papers

We study the problem of sampling from a probability distribution on $\mathbb R^p$ defined via a convex and smooth potential function. We consider a continuous-time diffusion-type process, termed Penalized Langevin dynamics (PLD), the drift…

Statistics Theory · Mathematics 2020-06-26 Avetik Karagulyan , Arnak S. Dalalyan

It is important to understand how dropout, a popular regularization method, aids in achieving a good generalization solution during neural network training. In this work, we present a theoretical derivation of an implicit regularization of…

Machine Learning · Computer Science 2023-04-11 Zhongwang Zhang , Zhi-Qin John Xu

The behavior of the self diffusion constant of Langevin particles interacting via a pairwise interaction is considered. The diffusion constant is calculated approximately within a perturbation theory in the potential strength about the bare…

Soft Condensed Matter · Physics 2009-11-10 D. S. Dean , A. Lefèvre

In this paper, we study the implicit regularization of stochastic gradient descent (SGD) through the lens of {\em dynamical stability} (Wu et al., 2018). We start by revising existing stability analyses of SGD, showing how the Frobenius…

Machine Learning · Statistics 2023-06-02 Lei Wu , Weijie J. Su

Backward diffusion is a prototype ill-posed evolution: high spatial frequencies grow exponentially in time, so mesh-based time marching without explicit regularization is quickly overwhelmed by noise. Schr\"odingerization embeds the…

Numerical Analysis · Mathematics 2026-05-19 Jeongbin Jo

Inverse problems and regularization theory is a central theme in contemporary signal processing, where the goal is to reconstruct an unknown signal from partial indirect, and possibly noisy, measurements of it. A now standard method for…

Optimization and Control · Mathematics 2014-12-09 Samuel Vaiter , Gabriel Peyré , Jalal M. Fadili

Large learning rates, when applied to gradient descent for nonconvex optimization, yield various implicit biases including the edge of stability (Cohen et al., 2021), balancing (Wang et al., 2022), and catapult (Lewkowycz et al., 2020).…

Machine Learning · Computer Science 2023-12-13 Yuqing Wang , Zhenghao Xu , Tuo Zhao , Molei Tao

Continuous time random walks and Langevin equations are two classes of stochastic models for describing the dynamics of particles in the natural world. While some of the processes can be conveniently characterized by both of them, more…

Statistical Mechanics · Physics 2019-01-28 Xudong Wang , Yao Chen , Weihua Deng

In this note, we consider the construction of a one-dimensional stable Langevin type process confined in the upper half-plane and submitted to reflective-diffusive boundary conditions whenever the particle position hits 0. We show that two…

Probability · Mathematics 2020-06-22 J. -F Jabir , C. Profeta

The inverse Langevin function is a fundamental part of the statistical chain models used to describe the behavior of polymeric-like materials, appearing also in other fields such as magnetism, molecular dynamics and even biomechanics. In…

Computational Physics · Physics 2020-07-15 José María Benitez , Francisco Javier Montáns

We demonstrate that the conventional path integral formulations generate inconsistent results exemplified by the geometric Brownian motion under the general stochastic interpretation. We thus develop a novel path integral formulation for…

Statistical Mechanics · Physics 2015-06-18 Ying Tang , Ruoshi Yuan , Ping Ao

We study how thermal fluctuations affect the dynamics of vortices in the two-dimensional classical, ferromagnetic, anisotropic Heisenberg model depending on their additive or multiplicative character. Using a collective coordinate theory,…

Condensed Matter · Physics 2009-10-31 Till Kamppeter , Franz G. Mertens , Esteban Moro , Angel Sanchez , A. R. Bishop

We discuss how to derive a Langevin equation (LE) in non standard systems, i.e. when the kinetic part of the Hamiltonian is not the usual quadratic function. This generalization allows to consider also cases with negative absolute…

Statistical Mechanics · Physics 2018-04-12 M. Baldovin , A. Puglisi , A. Vulpiani

Non-spherical particles transported by an anisotropic turbulent flow preferentially align with the mean shear and intermittently tumble when the local strain fluctuates. Such an intricate behaviour is here studied for inertialess,…

Soft Condensed Matter · Physics 2022-12-27 Lorenzo Campana , Mireille Bossy , Jeremie Bec

Fluctuations and noise may alter the behavior of dynamical systems considerably. For example, oscillations may be sustained by demographic fluctuations in biological systems where a stable fixed point is found in the absence of noise. We…

Adaptation and Self-Organizing Systems · Physics 2009-11-13 Richard P. Boland , Tobias Galla , Alan J. McKane

We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimization as presented in Raginsky et al. (2017). Non-asymptotic…

Statistics Theory · Mathematics 2021-02-03 Ngoc Huy Chau , Éric Moulines , Miklos Rásonyi , Sotirios Sabanis , Ying Zhang

For the Langevin model of the dynamics of a Brownian particle with perturbations orthogonal to its current velocity, in a regime when the particle velocity modulus becomes constant, an equation for the characteristic function $\psi…

Statistical Mechanics · Physics 2021-03-01 V. A. Doobko , S. V. Zubarev , E. V. Karachanskaya

Connected with the rise of interest in inverse problems is the development and analysis of regularization methods, which are a necessity due to the ill-posedness of inverse problems. Tikhonov-type regularization methods are very popular in…

Numerical Analysis · Mathematics 2021-03-16 Abinash Nayak

We study the problem of non-convex optimization using Stochastic Gradient Langevin Dynamics (SGLD). SGLD is a natural and popular variation of stochastic gradient descent where at each step, appropriately scaled Gaussian noise is added. To…

Machine Learning · Computer Science 2024-07-08 August Y. Chen , Ayush Sekhari , Karthik Sridharan

Injecting noise within gradient descent has several desirable features, such as smoothing and regularizing properties. In this paper, we investigate the effects of injecting noise before computing a gradient step. We demonstrate that small…

Machine Learning · Computer Science 2023-01-24 Antonio Orvieto , Anant Raj , Hans Kersting , Francis Bach