Forward-Backward Splitting for Optimal Transport Based Problems

Mireille El Gheche, Pascal Frossard, Guillermo Ortiz Jimenez, Hermina Petric Maretic, Effrosyni Simou
2020
Article de conférence

Résumé

Optimal transport aims to estimate a transportation plan that minimizes a displacement cost. This is realized by optimizing the scalar product between the sought plan and the given cost, over the space of doubly stochastic matrices. When the entropy regularization is added to the problem, the transportation plan can be efficiently computed with the Sinkhorn algorithm. Thanks to this breakthrough, optimal transport has been progressively extended to machine learning and statistical inference by introducing additional application-specific terms in the problem formulation. It is however challenging to design efficient optimization algorithms for optimal transport based extensions. To overcome this limitation, we devise a general forward-backward splitting algorithm based on Bregman distances for solving a wide range of optimization problems involving a differentiable function with Lipschitz-continuous gradient and a doubly stochastic constraint. We illustrate the efficiency of our approach in the context of continuous domain adaptation. Experiments show that the proposed method leads to a significant improvement in terms of speed and performance with respect to the state of the art for domain adaptation on a continually rotating distribution coming from the standard two moon dataset.

Official source

https://infoscience.epfl.ch/record/277617?ln=fr

À propos de ce résultat

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Concepts associés

Chargement

Publications associées

Chargement

Mean-Field methods for Structured Deep-Learning in Computer Vision

Pierre Bruno Baqué

In recent years, Machine Learning based Computer Vision techniques made impressive progress. These algorithms proved particularly efficient for image classification or detection of isolated objects. From a probabilistic perspective, these methods can predict marginals, over single or multiple variables, independently, with high accuracy. However, in many tasks of practical interest, we need to predict jointly several correlated variables. Practical applications include people detection in crowded scenes, image segmentation, surface reconstruction, 3D pose estimation and others. A large part of the research effort in today's computer-vision community aims at finding task-specific solutions to these problems, while leveraging the power of Deep-Learning based classifiers. In this thesis, we present our journey towards a generic and practical solution based on mean-field (MF) inference. Mean-field is a Statistical Physics-inspired method which has long been used in Computer-Vision as a variational approximation to posterior distributions over complex Conditional Random Fields. Standard mean-field optimization is based on coordinate descent and in many situations can be impractical. We therefore propose a novel proximal gradient-based approach to optimizing the variational objective. It is naturally parallelizable and easy to implement. We prove its convergence, and then demonstrate that, in practice, it yields faster convergence and often finds better optima than more traditional mean-field optimization techniques. Then, we show that we can replace the fully factorized distribution of mean-field by a weighted mixture of such distributions, that similarly minimizes the KL-Divergence to the true posterior. Our extension of the clamping method proposed in previous works allows us to both produce a more descriptive approximation of the true posterior and, inspired by the diverse MAP paradigms, fit a mixture of mean-field approximations. We demonstrate that this positively impacts real-world algorithms that initially relied on mean-fields. One of the important properties of the mean-field inference algorithms is that the closed-form updates are fully differentiable operations. This naturally allows to do parameter learning by simply unrolling multiple iterations of the updates, the so-called back-mean-field algorithm. We derive a novel and efficient structured learning method for multi-modal posterior distribution based on the Multi-Modal Mean-Field approximation, which can be seamlessly combined to modern gradient-based learning methods such as CNNs. Finally, we explore in more details the specific problem of structured learning and prediction for multiple-people detection in crowded scenes. We then present a mean-field based structured deep-learning detection algorithm that provides state of the art results on this dataset.

EPFL2018

Chargement

Contracts for Real-Time, Safety Critical Systems

Chandrakana Nandi

Verifying real-time systems goes beyond the verification of functional properties: it also requires the checking of real-time properties. This makes traditional contract-frameworks partially inept for checking real-time programs. This is a major problem because the failure of real-time and safety critical systems can have serious consequences. This thesis presents a solution to this problem by incorporating Design by Contract (annotating programs with function pre and post conditions) to such systems. The main contribution of this thesis is the development of a contract framework for cyclic real-time control applications written in C++. The contract framework allows the users to specify both functional and temporal properties for the applications. A novel approach of empirical cumulative distribution function (cdf ) based statistical inference is used for dynamically estimating temporal constraints and incorporating them in future contracts. The thesis also illustrates the use of Real-time Logic (RTL) for formal specification of the temporal properties. For evaluating our methodology, we have integrated it to a component-based framework called FASA (Future Automation System Architecture) developed at ABB Corporate Research for writing hard real time control applications. Experiments show that this contract framework can be smoothly integrated to existing control applications thereby increasing their reliability while having a acceptable overhead (less than 10%) on the performance.

2014

Chargement

Recent years have witnessed a rise in real-world data captured with rich structural information that can be better depicted by multi-relational or heterogeneous graphs.However, research on relational representation learning has so far mostly focused on the problems arising in simple, homogeneous graphs. Integrating the structural priors provided by multi-relational data may further empower the generalization capacity of representation learning models, yet it still remains an open challenge.Although there is a strong line of works on relational machine learning on knowledge graphs, it is quite concentrated on the task ofcompleting missing edges, which is known as link prediction. In this thesis, we shift the focus away from the well-addressed node and graph classification problems on simple graphs or the link prediction problem on knowledge graphs, and prompt new research questions targeting the representation learning problems that are overlooked in multi-relational data.First, we focus on the problem of node regression on multi-relational graphs, noting that inference of continuous node features across a graph is rather under-studied in the current relational learning research.We propose a novel propagation method which aims to complete missing features at the nodes of a multi-relational and directed graph.Our multi-relational propagation algorithm is composed of iterative neighborhood aggregations which originate from a relational local generative model. Our findings show the benefit of exploiting the inductive bias led by the multi-relational structure of the data.Next, we consider the node attribute completion problem in knowledge graphs, which is relatively unexplored by the knowledge graph reasoning literature.We propose a novel multi-relational attribute propagation method where we harness not only the relational structure of the knowledge graph, but also the dependencies between various types of numerical node attributes relying on a heterogeneous feature space.Our algorithm is framed within a message-passing scheme where the propagation parameters are estimated in advance. We also propose an alternative semi-supervised learning framework where the parameters and the missing node attributes are inferred in an end-to-end fashion.Experimental results on well-known knowledge graph datasets relay the effectiveness of our message-passing approach, which specifies the computational graph by the heterogeneity of the data.Finally, we study graph learning in multi-relational data domain.Unlike the existing structure inference methods, we aim at exploiting and combining each source of relational information provided by the data domain to learn the underlying graph of a set of observations.For this purpose, we employ a multi-layer graph representation which encodes multiple types of relationships between data entities. Then, we propose a mask learning method to infer a specific combination of the layers which reveals the structure of observations.Experiments conducted both on simulated and real-world data suggest that incorporating multi-relational domain knowledge enhances structure inference by boosting its adaptability to a variety of input data conditions.

EPFL2021

Chargement

EPFL2021

Mean-Field methods for Structured Deep-Learning in Computer Vision

Pierre Bruno Baqué

EPFL2018