Publications associées à Algorithme espérance-maximisation

Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization

Bayesian Optimization (BO) is typically used to optimize an unknown function f that is noisy and costly to evaluate, by exploiting an acquisition function that must be maximized at each optimization step. Even if provably asymptotically optimal BO algorith ...

2024

On the use of Cramér-Rao Lower Bound for least-variance circuit parameters identification of Li-ion cells

Mario Paolone, Vladimir Sovljanski

Electrochemical Impedance Spectroscopy (EIS) and Equivalent Circuit Models (ECMs) are widely used to characterize the impedance and estimate parameters of electrochemical systems such as batteries. We use a generic ECM with ten parameters grouped to model ...

2024

An Ordinal Latent Variable Model of Conflict Intensity

Robert West

Measuring the intensity of events is crucial for monitoring and tracking armed conflict. Advances in automated event extraction have yielded massive data sets of '' who did what to whom '' micro-records that enable datadriven approaches to monitoring confl ...

Assoc Computational Linguistics-Acl2023

Improving K-means Clustering Using Speculation

Anastasia Ailamaki, Viktor Sanca, Eleni Zapridou, Stefan Igescu

K-means is one of the fundamental unsupervised data clustering and machine learning methods. It has been well studied over the years: parallelized, approximated, and optimized for different cases and applications. With increasingly higher parallelism leadi ...

2023

Revisiting adversarial training for the worst-performing class

Volkan Cevher, Grigorios Chrysos, Thomas Michaelsen Pethick

Despite progress in adversarial training (AT), there is a substantial gap between the topperforming and worst-performing classes in many datasets. For example, on CIFAR10, the accuracies for the best and worst classes are 74% and 23%, respectively. We argu ...

2023

DeepNC: Deep Generative Network Completion

Andreas Oliver Spitz

Most network data are collected from partially observable networks with both missing nodes and missing edges, for example, due to limited resources and privacy settings specified by users on social media. Thus, it stands to reason that inferring the missin ...

IEEE COMPUTER SOC2022

A Benders decomposition for maximum simulated likelihood estimation of advanced discrete choice models

Michel Bierlaire, Claudia Bongiovanni

In this paper, we formulate a mixed integer linear program (MILP) for the simulated maximum likelihood estimation (MLSE) problem and devise a Benders decomposition approach to speed up the solution process. This framework can be applied to any advanced dis ...

2022

Hybrid Flock - Formation Control Algorithms

Alcherio Martinoli, Cyrill Silvan Baumann, Jonas Perolini, Emna Tourki

Two prominent categories for achieving coordinated multirobot displacement are flocking and navigation in formation. Both categories have their own body of literature and characteristics, including their respective advantages and disadvantages. While typic ...

Springer Nature Switzerland2022

Learning new physics from an imperfect machine

Raffaele Tito D'Agnolo, Andrea Wulzer

We show how to deal with uncertainties on the Standard Model predictions in an agnostic new physics search strategy that exploits artificial neural networks. Our approach builds directly on the specific Maximum Likelihood ratio treatment of uncertainties a ...

SPRINGER2022

Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization

Volkan Cevher, Alp Yurtsever, Maria-Luiza Vladarean

We propose a stochastic conditional gradient method (CGM) for minimizing convex finitesum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this template either suffer from slow convergence rates, or require carefully inc ...

2022

A Variational Inference Approach to Learning Multivariate Wold Processes

Patrick Thiran, Matthias Grossglauser, Negar Kiyavash, Seyed Jalal Etesami, William Trouleau

Temporal point-processes are often used for mathematical modeling of sequences of discrete events with asynchronous timestamps. We focus on a class of temporal point-process models called multivariate Wold processes (MWP). These processes are well suited t ...

MICROTOME PUBLISHING2021

Context-Aware Learning for Generative Models

José del Rocio Millán Ruiz, Ricardo Andres Chavarriaga Lozano, Robert Leeb, Serafeim Perdikis

This work studies the class of algorithms for learning with side-information that emerges by extending generative models with embedded context-related variables. Using finite mixture models (FMMs) as the prototypical Bayesian network, we show that maximum- ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2021

Simultaneous Perturbation Stochastic Approximation of the Quantum Fisher Information

Giuseppe Carleo, Julien Sebastian Gacon, Stefan Woerner

The Quantum Fisher Information matrix (QFIM) is a central metric in promising algorithms, such as Quantum Natural Gradient Descent and Variational Quantum Imaginary Time Evolution. Computing the full QFIM for a model with d parameters, however, is computat ...

VEREIN FORDERUNG OPEN ACCESS PUBLIZIERENS QUANTENWISSENSCHAF2021

Coordinating strategic aggregators in an active distribution network for providing operational flexibility

Sidi-Rachid Cherkaoui, Mokhtar Bozorg, Mohammad Rayati

The support of distributed energy resources (DERs) for providing operational flexibility can be beneficial from the transmission system operators' (TSOs') viewpoint. Despite all opportunities, using DERs within an active distribution network (ADN) for prov ...

Elsevier2020

Global Convergence and Variance Reduction for a Class of Nonconvex-Nonconcave Minimax Problems

Negar Kiyavash

Nonconvex minimax problems appear frequently in emerging machine learning applications, such as generative adversarial networks and adversarial learning. Simple algorithms such as the gradient descent ascent (GDA) are the common practice for solving these ...

2020

Robust Identification of Controlled Hawkes Processes

Thomas Alois Weber, Michael Mark

The identification of Hawkes-like processes can pose significant challenges. Despite substantial amounts of data, standard estimation methods show significant bias or fail to converge. To overcome these issues, we propose an alternative approach based on a ...

2020

A Catalyst Framework for Minimax Optimization

Negar Kiyavash

We introduce a generic two-loop scheme for smooth minimax optimization with strongly-convex-concave objectives. Our approach applies the accelerated proximal point framework (or Catalyst) to the associated dual problem and takes full advantage of existing ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2020

CPGD: Cadzow Plug-and-Play Gradient Descent for Generalised FRI

Martin Vetterli, Paul Hurley, Matthieu Martin Jean-André Simeoni, Adrien Georges Jean Besson

Finite rate of innovation (FRI) is a powerful reconstruction framework enabling the recovery of sparse Dirac streams from uniform low-pass filtered samples. An extension of this framework, called generalised FRI (genFRI), has been recently proposed for han ...

2020

Conditional Gradient Methods via Stochastic Path-Integrated Differential Estimator

Volkan Cevher, Alp Yurtsever

We propose a class of novel variance-reduced stochastic conditional gradient methods. By adopting the recent stochastic path-integrated differential estimator technique (SPIDER) of Fang et al. (2018) for the classical Frank-Wolfe (FW) method, we introduce ...

2019

Learning Hawkes Processes from a Handful of Events

Patrick Thiran, Matthias Grossglauser, William Trouleau, Farnood Salehi

Learning the causal-interaction network of multivariate Hawkes processes is a useful task in many applications. Maximum-likelihood estimation is the most common approach to solve the problem in the presence of long observation sequences. However, when only ...

2019