Publication
Proximal diffusion for stochastic costs with non-differentiable regularizers
Related publications (43)
Data-Driven Control and Optimization under Noisy and Uncertain Conditions
Control systems operating in real-world environments often face disturbances arising from measurement noise and model mismatch. These factors can significantly impact the perfor- mance and safety of the system. In this thesis, we aim to leverage data to de ...
EPFL2023Novel Ordering-based Approaches for Causal Structure Learning in the Presence of Unobserved Variables
We propose ordering-based approaches for learning the maximal ancestral graph (MAG) of a structural equation model (SEM) up to its Markov equivalence class (MEC) in the presence of unobserved variables. Existing ordering-based methods in the literature rec ...
Association for the Advancement of Artificial Intelligence (AAAI)2023Predicting in Uncertain Environments: Methods for Robust Machine Learning
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 ...
EPFL2022Optimization Over Banach Spaces: A Unified View on Supervised Learning and Inverse Problems
In this thesis, we reveal that supervised learning and inverse problems share similar mathematical foundations. Consequently, we are able to present a unified variational view of these tasks that we formulate as optimization problems posed over infinite-di ...
EPFL2022Utility/privacy trade-off as regularized optimal transport
Strategic information is valuable either by remaining private (for instance if it is sensitive) or, on the other hand, by being used publicly to increase some utility. These two objectives are antagonistic and leaking this information by taking full advant ...
SPRINGER HEIDELBERG2022Memory of Motion for Initializing Optimization in Robotics
Many robotics problems are formulated as optimization problems. However, most optimization solvers in robotics are locally optimal and the performance depends a lot on the initial guess. For challenging problems, the solver will often get stuck at poor loc ...
EPFL2022Adaptation in Stochastic Algorithms: From Nonsmooth Optimization to Min-Max Problems and Beyond
Stochastic gradient descent (SGD) and randomized coordinate descent (RCD) are two of the workhorses for training modern automated decision systems. Intriguingly, convergence properties of these methods are not well-established as we move away from the spec ...
EPFL2021Addressing fairness in classification with a model-agnostic multi-objective algorithm
Boi Faltings, Claudiu-Cristian Musat, Diego Matteo Antognini
The goal of fairness in classification is to learn a classifier that does not discriminate against groups of individuals based on sensitive attributes, such as race and gender. One approach to designing fair algorithms is to use relaxations of fairness not ...
2021Functional Penalised Basis Pursuit on Spheres
Matthieu Martin Jean-André Simeoni
In this work, we propose a unified theoretical and practical spherical approximation framework for functional inverse problems on the hypersphere. More specifically, we consider recovering spherical fields directly in the continuous domain using functional ...
2020Maximum-likelihood estimation of kinetic parameters via the extent-based incremental approach
Dominique Bonvin, Julien Léo Billeter, Diogo Filipe Mateus Rodrigues
For lumped homogeneous reaction systems, this paper presents a kinetic model identification scheme that provides maximum-likelihood parameter estimates and guarantees convergence to global optimality. The use of the extent-based incremental approach allows ...
PERGAMON-ELSEVIER SCIENCE LTD2019