Publications associées à Multi-Level Monte Carlo Methods for Uncertainty Quantification and Risk-Averse Optimisation

Publications associées (46)

What can radars tell us about snowfall microphysics? Insights from a Markov chain Monte-Carlo approach

Alexis Berne, Anne-Claire Marie Billault--Roux

Multi-frequency and Doppler spectral radars are valuable tools for retrieving information on the microphysics of precipitation, particularly snowfall. However, estimating microphysical properties from radar measurements is an ill-posed problem, i.e., diffe ...

American Meteorological Society2025

Quantifying the Unknown: Data-Driven Approaches and Applications in Energy Systems

Paul Scharnhorst

In light of the challenges posed by climate change and the goals of the Paris Agreement, electricity generation is shifting to a more renewable and decentralized pattern, while the operation of systems like buildings is increasingly electrified. This calls ...

EPFL2024

Study of the decay (Formula presented)

Yunxuan Song

Using (Formula presented) (Formula presented) events collected with the BESIII detector operating at the BEPCII collider, we have observed the decay (Formula presented) for the first time with a statistical significance of (Formula presented). Its branchin ...

2025

On the Generalization of Stochastic Gradient Descent with Momentum

Volkan Cevher, Kimon Antonakopoulos

While momentum-based accelerated variants of stochastic gradient descent (SGD) are widely used when training machine learning models, there is little theoretical understanding on the generalization error of such methods. In this work, we first show that th ...

Microtome Publishing2024

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

Fernando Porté Agel, Jiannong Fang, Wenlong Liao

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 ...

2025

Scalable constrained optimization

Maria-Luiza Vladarean

Modern optimization is tasked with handling applications of increasingly large scale, chiefly due to the massive amounts of widely available data and the ever-growing reach of Machine Learning. Consequently, this area of research is under steady pressure t ...

EPFL2024

Crypto market betas: the limits of predictability and hedging

Thomas Alois Weber, Michael Mark

This article analyzes the predictability of market betas concerning cryptocurrency assets and evaluates the efficiency of beta-hedged, market-neutral portfolios. We forecast 1-year-ahead market betas using various estimating methods, including ordinary lea ...

Springer Science and Business Media LLC2025

Adaptive Finite Elements with Large Aspect Ratio. Application to Aluminium Electrolysis

Paride Passelli

The goal of this work is to use anisotropic adaptive finite elements for the numerical simulation of aluminium electrolysis. The anisotropic adaptive criteria are based on a posteriori error estimates derived for simplified problems. First, we consider an ...

EPFL2024

Data-driven control in atomic force microscopy using a genetic algorithm

Alireza Karimi, Georg Fantner

Increasing the scanning speed in Atomic Force Microscopy (AFM) relies on improving the tracking performance in the vertical direction of motion. The lightly damped resonances of piezo-actuators utilized in AFM nano-positioning stages hinder the maximum ach ...

2025

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Anastasiia Koloskova

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

EPFL2024

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

Volkan Cevher, Fanghui Liu, Zhenyu Zhu

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 ...

2025

Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning

Philippe Schwaller, Jeff Guo

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparen ...

Amer Chemical Soc2024

Foundations of a New Learning Paradigm in AI Grounded in the Principles of Evolutionary Developmental Biology

Zeki Doruk Erden

Contemporary AI faces important limitations that remain unresolved despite significant successes. Chief among these are the inability to acquire new knowledge without destroying old, the incomprehensible and nonengineerable nature of internal representatio ...

EPFL2025

Mesh-based topology, shape and sizing optimization of ribbed plates

Ahmad Abdulrahman Ahmad Majdouba

In this paper, we present a new parameterization and optimization procedure for minimizing the weight of ribbed plates. The primary goal is to reduce embodied CO2 in concrete floors as part of the effort to diminish the carbon footprint of the construction ...

Springer2024

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

Zaffar Ahmed Shaikh

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 ...

SAGE PUBLICATIONS LTD2025

The effect of smooth parametrizations on nonconvex optimization landscapes

Nicolas Boumal

We develop new tools to study landscapes in nonconvex optimization. Given one optimization problem, we pair it with another by smoothly parametrizing the domain. This is either for practical purposes (e.g., to use smooth optimization algorithms with good g ...

Springer Heidelberg2024

Learning to Assemble with Alternative Plans

Gabriel Rémi Vallat, Maryam Kamgarpour, Stefana Parascho, Ziqi Wang, Jingwen Wang

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 ...

Association for Computing Machinery (ACM)2025

A new flexible multiple discrete–continuous extreme value (MDCEV) choice model: exploring non-monotonic preference in time use decisions

Michel Bierlaire

Derived from the Karush–Kuhn–Tucker (KKT) optimality conditions of utility maximization, the multiple discrete–continuous extreme value (MDCEV) models are extensively used in the field of time use. This is because they are grounded in a framework that maxi ...

2025

Graph generative deep learning models with an application to circuit topologies

Igor Krawczuk

Modern integrated circuits are tiny yet incredibly complex technological artifacts, composed of millions and billions of individual structures working in unison. Managing their complexity and facilitating their design drove part of the co-evolution of mode ...

EPFL2024

ERGODICITY OF 2D SINGULAR STOCHASTIC NAVIER–STOKES EQUATIONS

Martin Hairer

We consider the 2D stochastic Navier–Stokes equations driven by noise that have the regularity of space-time white noise but don’t exactly coincide with it. We show that, provided that the intensity of the noise is sufficiently weak at high frequencies, th ...

2025