Publications associées à An Efficient Sampling Algorithm for Non-smooth Composite Potentials

Gibbs sampling the posterior of neural networks

Giovanni Piccioli, Lenka Zdeborová, Emanuele Troiani

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 ...

Iop Publishing Ltd2024

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

A ride time-oriented scheduling algorithm for dial-a-ride problems

Nikolaos Geroliminis, Claudia Bongiovanni, Mor Kaspi

This paper offers a new algorithm to efficiently optimize scheduling decisions for dial-a-ride problems (DARPs), including problem variants considering electric and autonomous vehicles (e-ADARPs). The scheduling heuristic, based on linear programming theor ...

Pergamon-Elsevier Science Ltd2024

MIXING FOR GENERIC ROUGH SHEAR FLOWS

Lucio Galeati

We study mixing and diffusion properties of passive scalars driven by generic rough shear flows. Genericity is here understood in the sense of prevalence, and (ir)regularity is measured in the Besov-Nikolskii scale B\alpha 1,\infty, \alpha \in (0,1). We pr ...

Siam Publications2023

Analysis of a Class of Multilevel Markov Chain Monte Carlo Algorithms Based on Independent Metropolis–Hastings

Fabio Nobile, Juan Pablo Madrigal Cianci

In this work, we present, analyze, and implement a class of multilevel Markov chain Monte Carlo(ML-MCMC) algorithms based on independent Metropolis--Hastings proposals for Bayesian inverse problems. In this context, the likelihood function involves solving ...

2023

Fixing by Mixing: A Recipe for Optimal Byzantine ML under Heterogeneity

Rachid Guerraoui, John Stephan, Sadegh Farhadkhani, Nirupam Gupta, Rafaël Benjamin Pinot, Youssef Allouah

Byzantine machine learning (ML) aims to ensure the resilience of distributed learning algorithms to misbehaving (or Byzantine) machines. Although this problem received significant attention, prior works often assume the data held by the machines to be homo ...

PMLR2023

Fast Parallel Algorithms for Enumeration of Simple, Temporal, and Hop-Constrained Cycles

Paolo Ienne, Kubilay Atasu, Jovan Blanusa

Finding cycles in directed graphs enables important applications in various domains such as finance, biology, chemistry, and network science. However, as the size of graph datasets continues to grow, it becomes increasingly difficult to discover cycles wit ...

arXiv2023

Benign Overfitting in Deep Neural Networks under Lazy Training

Volkan Cevher, Zhenyu Zhu, Grigorios Chrysos, Fanghui Liu

This paper focuses on over-parameterized deep neural networks (DNNs) with ReLU activation functions and proves that when the data distribution is well-separated, DNNs can achieve Bayesoptimal test error for classification while obtaining (nearly) zero-trai ...

2023

Finding stationary points on bounded-rank matrices: a geometric hurdle and a smooth remedy

Nicolas Boumal

We consider the problem of provably finding a stationary point of a smooth function to be minimized on the variety of bounded-rank matrices. This turns out to be unexpectedly delicate. We trace the difficulty back to a geometric obstacle: On a nonsmooth se ...

SPRINGER HEIDELBERG2022

Spectral analysis for transmission eigenvalue problems with and without the complementing conditions

Jean Louis-Alexandre Fornerod

The interior transmission eigenvalue problem is a system of partial differential equations equipped with Cauchy data on the boundary: the transmission conditions. This problem appears in the inverse scattering theory for inhomogeneous media when, for some ...

EPFL2022

VL4Pose: Active Learning Through Out-Of-Distribution Detection For Pose Estimation

Alexandre Massoud Alahi, Megh Hiren Shukla

Advances in computing have enabled widespread access to pose estimation, creating new sources of data streams. Unlike mock set-ups for data collection, tapping into these data streams through on-device active learning allows us to directly sample from the ...

BMVA Press2022

Geometrical Treatise on the Modelling of 3D Particulate Inclusion-Matrix Microstructures with an Application to Historical Stone Masonry Walls

Mahmoud S. M. Shaqfa

As historical stone masonry structures are vulnerable and prone to damage in earthquakes, investigating their structural integrity is important to reduce injuries and casualties while preserving their historical value. Stone masonry is a composite material ...

EPFL2022

Variational Methods For Continuous-Domain Inverse Problems: the Quest for the Sparsest Solution

Thomas Jean Debarre

The goal of this thesis is to study continuous-domain inverse problems for the reconstruction of sparse signals and to develop efficient algorithms to solve such problems computationally. The task is to recover a signal of interest as a continuous function ...

EPFL2022

Learning to Represent and Reconstruct 3D Deformable Objects

Jan Bednarík

Representing and reconstructing 3D deformable shapes are two tightly linked problems that have long been studied within the computer vision field. Deformable shapes are truly ubiquitous in the real world, whether be it specific object classes such as human ...

EPFL2022

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

Predicting in Uncertain Environments: Methods for Robust Machine Learning

Paul Thierry Yves Rolland

One of the main goal of Artificial Intelligence is to develop models capable of providing valuable predictions in real-world environments. In particular, Machine Learning (ML) seeks to design such models by learning from examples coming from this same envi ...

EPFL2022

Equivalence Checking for Orthocomplemented Bisemilattices in Log-Linear Time

Viktor Kuncak, Simon Guilloud

We present a quasilinear time algorithm to decide the word problem on a natural algebraic structures we call orthocomplemented bisemilattices, a subtheory of boolean algebra. We use as a base a variation of Hopcroft, Ullman and Aho algorithm for tree isomo ...

Springer2022

HIERARCHICAL MARKOV CHAIN MONTE CARLO METHODS FOR BAYESIAN INVERSE PROBLEMS

Juan Pablo Madrigal Cianci

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 base ...

EPFL2022

High-order geometric integrators for nonadiabatic molecular quantum dynamics and their applications to explore conical intersections

Seonghoon Choi

Accurate simulations of molecular quantum dynamics are crucial for understanding numerous natural processes and experimental results. Yet, such high-accuracy simulations are challenging even for relatively simple systems where the Born-Oppenheimer approxim ...

EPFL2022

Distributionally Robust Optimization with Markovian Data

Daniel Kuhn, Tobias Sutter, Mengmeng Li

We study a stochastic program where the probability distribution of the uncertain problem parameters is unknown and only indirectly observed via finitely many correlated samples generated by an unknown Markov chain with d states. We propose a data-driven d ...

JMLR-JOURNAL MACHINE LEARNING RESEARCH2021