English
Related papers

Related papers: Stochastic automatic differentiation and the Signa…

200 papers

In this paper, we consider a novel machine learning problem, that is, learning a classifier from noisy label distributions. In this problem, each instance with a feature vector belongs to at least one group. Then, instead of the true label…

Machine Learning · Computer Science 2017-08-17 Yuya Yoshikawa

The problem of differentiating a function with bounded second derivative in the presence of bounded measurement noise is considered in both continuous-time and sampled-data settings. Fundamental performance limitations of causal…

Systems and Control · Electrical Eng. & Systems 2023-03-28 Richard Seeber , Hernan Haimovich

Nonlinear stochastic differential equations provide one of the mathematical models yielding 1/f noise. However, the drawback of a single equation as a source of 1/f noise is the necessity of power-law steady-state probability density of the…

Statistical Mechanics · Physics 2016-05-25 J. Ruseckas , R Kazakevičius , B Kaulakys

We consider an unconstrained problem of minimizing a smooth convex function which is only available through noisy observations of its values, the noise consisting of two parts. Similar to stochastic optimization problems, the first part is…

Optimization and Control · Mathematics 2020-09-22 Eduard Gorbunov , Pavel Dvurechensky , Alexander Gasnikov

We analyze the statistical mechanical properties of n-detectors in arbitrary states of motion interacting with each other via a quantum field. We use the open system concept and the influence functional method to calculate the influence of…

General Relativity and Quantum Cosmology · Physics 2009-10-28 Alpan Raval , B. L. Hu , James Anglin

We consider the dynamic linear regression problem, where the predictor vector may vary with time. This problem can be modeled as a linear dynamical system, with non-constant observation operator, where the parameters that need to be learned…

Machine Learning · Computer Science 2022-10-13 Mark Kozdoba , Edward Moroshko , Shie Mannor , Koby Crammer

Stochastic differential equations (SDEs) are a ubiquitous modeling framework that finds applications in physics, biology, engineering, social science, and finance. Due to the availability of large-scale data sets, there is growing interest…

Machine Learning · Statistics 2025-03-04 Ziheng Guo , James Greene , Ming Zhong

The computation of the glueball spectrum is particularly challenging due to the rapid decay of the signal-to-noise ratio of the correlation functions. To address this issue, advanced techniques such as gauge link smearing and the…

High Energy Physics - Lattice · Physics 2023-12-19 Lorenzo Barca , Francesco Knechtli , Michael Peardon , Stefan Schaefer , Juan Andrés Urrea-Niño

Non-perturbative formulations of field theories are essential to capture intriguing physical phenomena, including confinement in QCD, spontaneous supersymmetry breaking, and dynamical compactification in superstrings. Lattice regularization…

High Energy Physics - Lattice · Physics 2023-09-08 Arpith Kumar

In this paper, we present a novel derivative-free optimization framework for solving unconstrained stochastic optimization problems. Many problems in fields ranging from simulation optimization to reinforcement learning involve settings…

Optimization and Control · Mathematics 2024-04-19 Raghu Bollapragada , Cem Karamanli , Stefan M. Wild

Path integral contour deformations have been shown to mitigate sign and signal-to-noise problems associated with phase fluctuations in lattice field theories. We define a family of contour deformations applicable to $SU(N)$ lattice gauge…

High Energy Physics - Lattice · Physics 2021-06-02 William Detmold , Gurtej Kanwar , Henry Lamm , Michael L. Wagman , Neill C. Warrington

We introduce a novel and efficient algorithm called the stochastic approximate gradient descent (SAGD), as an alternative to the stochastic gradient descent for cases where unbiased stochastic gradients cannot be trivially obtained.…

Machine Learning · Computer Science 2020-02-14 Yixuan Qiu , Xiao Wang

One crucial factor behind the success of deep learning lies in the implicit bias induced by noise inherent in gradient-based training algorithms. Motivated by empirical observations that training with noisy labels improves model…

Machine Learning · Computer Science 2026-03-12 Tongcheng Zhang , Zhanpeng Zhou , Mingze Wang , Andi Han , Wei Huang , Taiji Suzuki , Junchi Yan

Diffusion models are currently the leading generative AI approach used for image generation in e.g. DALL-E and Stable Diffusion. In this talk we relate diffusion models to stochastic quantisation in field theory and employ it to generate…

High Energy Physics - Lattice · Physics 2024-12-19 Gert Aarts , Lingxiao Wang , Kai Zhou

We consider the problem of minimizing a $d$-dimensional Lipschitz convex function using a stochastic gradient oracle. We introduce and motivate a setting where the noise of the stochastic gradient is isotropic in that it is bounded in every…

Optimization and Control · Mathematics 2025-10-24 Annie Marsden , Liam O'Carroll , Aaron Sidford , Chenyi Zhang

The distance transform (DT) and its many variations are ubiquitous tools for image processing and analysis. In many imaging scenarios, the images of interest are corrupted by noise. This has a strong negative impact on the accuracy of the…

Computer Vision and Pattern Recognition · Computer Science 2020-09-14 Johan Öfverstedt , Joakim Lindblad , Nataša Sladoje

We give a full account of the Numerical Stochastic Perturbation Theory method for Lattice Gauge Theories. Particular relevance is given to the inclusion of dynamical fermions, which turns out to be surprisingly cheap in this context. We…

High Energy Physics - Lattice · Physics 2008-11-26 F. Di Renzo , L. Scorzato

Real-time lattice quantum electrodynamics (QED) provides a unique tool for simulating plasmas in the strong-field regime, where collective plasma scales are not well-separated from relativistic-quantum scales. As a toy model, we study…

Plasma Physics · Physics 2018-05-16 Yuan Shi , Jianyuan Xiao , Hong Qin , Nathaniel J. Fisch

We present a new method for the separation of superimposed, independent, auto-correlated components from noisy multi-channel measurement. The presented method simultaneously reconstructs and separates the components, taking all channels…

Methodology · Statistics 2018-02-14 Jakob Knollmüller , Torsten A. Enßlin

The Stochastic Backscatter Model involves the generation of a set of random variables characterised by prescribed correlations in space and time. These variables are obtained by smoothing an initially uncorrelated random field, which…

Computational Physics · Physics 2025-11-12 Angelo Passariello
‹ Prev 1 8 9 10 Next ›