Publications related to Global optimization

HIERARCHICAL MARKOV CHAIN MONTE CARLO METHODS FOR BAYESIAN INVERSE PROBLEMS

This thesis is devoted to the construction, analysis, and implementation of two types of hierarchical Markov Chain Monte Carlo (MCMC) methods for the solution of large-scale Bayesian Inverse Problems (BIP).The first hierarchical method we present is based ...

EPFL2022

Bridging the gap between model-driven and data-driven methods in the era of Big Data

Gael Lederrey

Data-driven and model-driven methodologies can be regarded as competitive fields since they tackle similar problems such as prediction. However, these two fields can learn from each other to improve themselves. Indeed, data-driven methodologies have been d ...

EPFL2022

Proximal Point Imitation Learning

Volkan Cevher, Luca Viano, Igor Krawczuk, Angeliki Kamoutsi

This work develops new algorithms with rigorous efficiency guarantees for infinite horizon imitation learning (IL) with linear function approximation without restrictive coherence assumptions. We begin with the minimax formulation of the problem and then o ...

2022

Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function

Patrick Thiran, Negar Kiyavash, Saber Salehkaleybar

We study the performance of Stochastic Cubic Regularized Newton (SCRN) on a class of functions satisfying gradient dominance property with

1\le\alpha\le2

which holds in a wide range of applications in machine learning and signal processing. This conditio ...

NeurIPS2022

Overcoming decision paralysis—A digital twin for decision making in energy system design

François Maréchal, Tuong-Van Nguyen, Julia Granacher

The design of efficient energy systems, through the development of new technologies and the improvement of current ones, requires the use of rigorous process synthesis methods for generating and analysing design alternatives. We introduce a digital twin of ...

2022

A Noise-Resistant Mixed-Discrete Particle Swarm Optimization Algorithm for the Automatic Design of Robotic Controllers

Alcherio Martinoli, Cyrill Silvan Baumann

The automatic design of well-performing robotic controllers is still an unsolved problem due to the inherently large parameter space and noisy, often hard-to-define performance metrics, especially when sequential tasks need to be accomplished. Distal contr ...

2022

A universal workflow for creation, validation and generalization of detailed neuronal models

Henry Markram, Srikanth Ramaswamy, Werner Alfons Hilda Van Geit, Alexis Arnaudon, Maria Reva, Mustafa Anil Tuncel, Darshan Mandge, Christian Andreas Rössert, Tanguy Pierre Louis Damart

Detailed single neuron modeling is widely used to study neuronal functions. While cellular and functional diversity across the mammalian cortex is vast, most of the available computational tools are dedicated to the reproduction of a small set of specific ...

2022

Material removing tool and method for designing the same

Jean-François Molinari, Son-Jonathan Pham-Ba

The invention relates to a material removing tool, such as an ice cream scoop, and method for designing the same. The material removing tool has a shape optimized to minimize the amount of work the user has to provide in order to form and remove a piece of ...

2022

Sharp asymptotics on the compression of two-layer neural networks

Marco Mondelli

In this paper, we study the compression of a target two-layer neural network with N nodes into a compressed network with M < N nodes. More precisely, we consider the setting in which the weights of the target network are i.i.d. sub-Gaussian, and we minimiz ...

IEEE2022

Frequency-domain data-driven position-dependent controller synthesis for Cartesian Robots

Alireza Karimi, Philippe Louis Schuchert

Cartesian robots have position-dependent dynamics that should be accounted for in high performance applications. Traditional methods design Linear Time Invariant (LTI) controllers which are robustly stable with respect to position variations, but require a ...

2022

Global optimization

Graph Chatbot

Chat with Graph Search

HIERARCHICAL MARKOV CHAIN MONTE CARLO METHODS FOR BAYESIAN INVERSE PROBLEMS

Bridging the gap between model-driven and data-driven methods in the era of Big Data

Proximal Point Imitation Learning

Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function

Overcoming decision paralysis—A digital twin for decision making in energy system design

A Noise-Resistant Mixed-Discrete Particle Swarm Optimization Algorithm for the Automatic Design of Robotic Controllers

A universal workflow for creation, validation and generalization of detailed neuronal models

Material removing tool and method for designing the same

Sharp asymptotics on the compression of two-layer neural networks

Frequency-domain data-driven position-dependent controller synthesis for Cartesian Robots

Bridging the gap between model-driven and data-driven methods in the era of Big Data

Sharp asymptotics on the compression of two-layer neural networks

HIERARCHICAL MARKOV CHAIN MONTE CARLO METHODS FOR BAYESIAN INVERSE PROBLEMS

Overcoming decision paralysis—A digital twin for decision making in energy system design

Proximal Point Imitation Learning

Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Function

Frequency-domain data-driven position-dependent controller synthesis for Cartesian Robots

A universal workflow for creation, validation and generalization of detailed neuronal models

A Noise-Resistant Mixed-Discrete Particle Swarm Optimization Algorithm for the Automatic Design of Robotic Controllers

Material removing tool and method for designing the same