Quantitative convergence rates for scaling limit of SPDEs with transport noise

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

This paper investigates the fundamental regression task of learning k neurons (a.k.a. teachers) from Gaussian input, using two-layer ReLU neural networks with width m (a.k.a. students) and m, k = O(1), trained via gradient descent under proper initializati ...

We present a reinforcement learning framework for constructing assemblies composed of rigid parts, which are commonly seen in many historical masonry buildings and bridges. Traditional construction methods for such structures often depend on dense scaffold ...

In recent years, neural quantum states have emerged as a powerful variational approach, achieving state-of-the-art accuracy when representing the ground-state wave function of a great variety of quantum many-body systems, including spin lattices, interacti ...

Animals have to navigate complex environments and perform intricate swimming maneuvers in the real world. To conquer these challenges, animals evolved a variety of motion control strategies. While it is known that many factors contribute to motion control, ...

As one of the major threats to women's health worldwide, breast cancer requires early diagnosis and accurate classification, since they are key to optimizing therapeutic interventions and ensuring precise prognosis. Recently, deep learning has demonstrated ...

Deploying energy-efficient deep neural networks on energy-constrained edge devices is an important research topic in both machine learning and circuit design communities. Both artificial neural networks (ANNs) and spiking neural networks (SNNs) have been p ...

Deep neural networks (DNNs) are receiving increasing attention in wind power forecasting due to their ability to effectively capture complex patterns in wind data. However, their forecast errors are severely limited by the local optimal weight issue in opt ...

Now is an exciting time for the domain of Earth observation (EO), with a multitude of diverse sensors looking at the planet from satellites, airplanes or drones. The volume of imagery acquired is massive, and hold great potential for a variety of applicati ...

High-dimensional data must be highly structured to be learnable. Although the compositional and hierarchical nature of data is often put forward to explain learnability, quantitative measurements establishing these properties are scarce. Likewise, accessin ...

We present a numerical model for the approximation of multiphase flows with free surfaces and strong interfacial effects. The model relies on the multiphase incompressible Navier-Stokes equations, and includes surface tension effects on the interfaces betw ...

This thesis introduces spectroscopy-free Raman biosensing, which may find increasing use in the next generation of wearable devices for preventive healthcare. While wearables have made substantial advancements in detecting physical biomarkers, they have ye ...

In this work we consider solutions to stochastic partial differential equations with transport noise, which are known to converge, in a suitable scaling limit, to solution of the corresponding deterministic PDE with an additional viscosity term. Large devi ...

We study the existence, uniqueness, and regularity of the solution to the stochastic reaction-diffusion equation (SRDE) with colored noise F-center dot:partial derivative(t)u = aijuxixj +biuxi + cu - bu1+beta +xi u1+gamma F-center dot, (t, x) is ...

Using a variational method, we prove the existence of heteroclinic solutions for a 6-dimensional system of ordinary differential equations. We derive this system from the classical Benard-Rayleigh problem near the convective instability threshold. The cons ...

The thesis is dedicated to the study of two main partial differential equations (PDEs) in fluid dynamics: the Navier-Stokes equations, which describe the motion of incompressible fluids, and the transport equation with divergence-free velocity fields, whic ...

This paper establishes a mean-field equation set and an energy theorem to provide a theoretical basis in view of the development of self-consistent, physics-based turbulent transport models for mean-field transport codes. A rigorous averaging procedure ide ...

A space-time adaptive algorithm is presented to solve the incompressible Navier-Stokes equations. Time discretization is performed with the BDF2 method while continuous, piecewise linear anisotropic finite elements are used for the space discretization. Th ...

Deep digital twins (DDTs) are deep neural networks that encode the behavior of complex physical systems. DDTs are excellent system representations due to their ability to continuously adapt to operational changes and their capability to capture complex rel ...

In this paper, we study sampling from a posterior derived from a neural network. We propose a new probabilistic model consisting of adding noise at every pre- and post-activation in the network, arguing that the resulting posterior can be sampled using an ...

In impermeable media, a hydraulic fracture can continue to expand even without additional fluid injection if its volume exceeds the limiting volume of a hydrostatically loaded radial fracture. This limit depends on the mechanical properties of the surround ...

Quantitative convergence rates for scaling limit of SPDEs with transport noise

Chat with Graph Search

How Gradient Descent Balances Features: A Dynamical Analysis For Two-Layer Neural Networks

Learning to Assemble with Alternative Plans

Accurate neural quantum states for interacting lattice bosons

Using deep reinforcement learning to investigate stretch feedback during swimming of the lamprey

Mspo: a Machine Learning Hyperparameter Optimization Method for Enhanced Breast Cancer Image Classification

Eflop: a Sparsity-aware Metric for Evaluating Computational Cost in Spiking and Non-spiking Neural Networks

Improving the accuracy and interpretability of neural networks for wind power forecasting

Interact with Earth Observation Images using AI: Transparent Methods and Evaluation for Visual Question Answering

Probing the latent hierarchical structure of data via diffusion models

A cut-cell method for the numerical simulation of 3D multiphase flows with strong interfacial effects

Toward Wearable Biosensing by Spectroscopy-free Raman Shift Detection and Soft Optofluidics

LDP and CLT for SPDEs with transport noise

Lp-regularity theory for the stochastic reaction-diffusion equation with super-linear multiplicative noise and strong dissipativity

Heteroclinic orbits for a system of amplitude equations for orthogonal domain walls

Anomalous dissipation and other non-smooth phenomena in fluids

Mean-field transport equations and energy theorem for plasma edge turbulent transport

An adaptive space-time algorithm for the incompressible Navier-Stokes equations

Digital Twin Generalization with Meta and Geometric Deep Learning

Gibbs sampling the posterior of neural networks

Three-dimensional buoyant hydraulic fractures: finite volume release