Search Results for author: Jean-Charles Delvenne

Found 16 papers, 10 papers with code

Efficiency Separation between RL Methods: Model-Free, Model-Based and Goal-Conditioned

no code implementations28 Sep 2023 Brieuc Pinon, Raphaël Jungers, Jean-Charles Delvenne

We prove a fundamental limitation on the efficiency of a wide class of Reinforcement Learning (RL) algorithms.

Reinforcement Learning (RL)

A model-based approach to meta-Reinforcement Learning: Transformers and tree search

no code implementations24 Aug 2022 Brieuc Pinon, Jean-Charles Delvenne, Raphaël Jungers

Meta-Reinforcement Learning (meta-RL) methods demonstrate a capability to learn behaviors that efficiently acquire and exploit information in several meta-RL problems.

Meta-Learning Meta Reinforcement Learning +2

PAC-learning gains of Turing machines over circuits and neural networks

no code implementations23 Mar 2021 Brieuc Pinon, Raphaël Jungers, Jean-Charles Delvenne

We provide lower and upper bounds on the potential gains in sample efficiency between the MDL applied with Turing machines instead of ANNs.

PAC learning

Stochastic Thermodynamics of Non-Linear Electronic Circuits: A Realistic Framework for Computing around kT

1 code implementation24 Aug 2020 Nahuel Freitas, Jean-Charles Delvenne, Massimiliano Esposito

We present a general formalism for the construction of thermodynamically consistent stochastic models of non-linear electronic circuits.

Statistical Mechanics

Severability of mesoscale components and local time scales in dynamical networks

2 code implementations4 Jun 2020 Yun William Yu, Jean-Charles Delvenne, Sophia N. Yaliraki, Mauricio Barahona

A major goal of dynamical systems theory is the search for simplified descriptions of the dynamics of a large number of interacting states.

Image Segmentation Semantic Segmentation

Multi-scale Anomaly Detection on Attributed Networks

1 code implementation25 Nov 2019 Leonardo Gutiérrez-Gómez, Alexandre Bovet, Jean-Charles Delvenne

Many social and economic systems can be represented as attributed networks encoding the relations between entities who are themselves described by different node attributes.

Social and Information Networks Physics and Society

Network constraints on the mixing patterns of binary node metadata

1 code implementation13 Aug 2019 Matteo Cinelli, Leto Peel, Antonio Iovanella, Jean-Charles Delvenne

We consider the network constraints on the bounds of the assortativity coefficient, which measures the tendency of nodes with the same attribute values to be interconnected.

Social and Information Networks Data Analysis, Statistics and Probability Physics and Society

Unsupervised Network Embedding for Graph Visualization, Clustering and Classification

1 code implementation25 Feb 2019 Leonardo Gutiérrez-Gómez, Jean-Charles Delvenne

In this work we provide an unsupervised approach to learn embedding representation for a collection of graphs so that it can be used in numerous graph mining tasks.

Classification Clustering +4

Measuring the effect of node aggregation on community detection

1 code implementation24 Sep 2018 Yérali Gandica, Adeline Decuyper, Christophe Cloquet, Isabelle Thomas, Jean-Charles Delvenne

Many times the nodes of a complex network, whether deliberately or not, are aggregated for technical, ethical, legal limitations or privacy reasons.

Physics and Society Social and Information Networks

Multi-hop assortativities for networks classification

1 code implementation14 Sep 2018 Leonardo Gutierrez Gomez, Jean-Charles Delvenne

Several social, medical, engineering and biological challenges rely on discovering the functionality of networks from their structure and node metadata, when it is available.

Classification General Classification

Multiscale dynamical embeddings of complex networks

2 code implementations10 Apr 2018 Michael T. Schaub, Jean-Charles Delvenne, Renaud Lambiotte, Mauricio Barahona

Complex systems and relational data are often abstracted as dynamical processes on networks.

Social and Information Networks Systems and Control Physics and Society

Modelling structure and predicting dynamics of discussion threads in online boards

1 code implementation30 Jan 2018 Alexey N. Medvedev, Jean-Charles Delvenne, Renaud Lambiotte

We compare the efficiency of our approach with previous works and show its superiority for the prediction of the dynamics of discussions.

Social and Information Networks Probability Data Analysis, Statistics and Probability 90B18, 60K35, 60G55, 82C99

Positive semi-definite embedding for dimensionality reduction and out-of-sample extensions

1 code implementation20 Nov 2017 Michaël Fanuel, Antoine Aspeel, Jean-Charles Delvenne, Johan A. K. Suykens

In machine learning or statistics, it is often desirable to reduce the dimensionality of a sample of data points in a high dimensional space $\mathbb{R}^d$.

Dimensionality Reduction

Dynamics Based Features For Graph Classification

no code implementations30 May 2017 Leonardo Gutierrez Gomez, Benjamin Chiem, Jean-Charles Delvenne

Numerous social, medical, engineering and biological challenges can be framed as graph-based learning tasks.

General Classification Graph Classification

Random Multi-Hopper Model. Super-Fast Random Walks on Graphs

no code implementations24 Dec 2016 Ernesto Estrada, Jean-Charles Delvenne, Naomichi Hatano, José L. Mateos, Ralf Metzler, Alejandro P. Riascos, Michael T. Schaub

Stated differently, for small parameter values the multi-hopper explores a general graph as fast as possible when compared to a random walker on a full graph.

Physics and Society Statistical Mechanics Social and Information Networks Mathematical Physics Mathematical Physics Probability

The many facets of community detection in complex networks

no code implementations23 Nov 2016 Michael T. Schaub, Jean-Charles Delvenne, Martin Rosvall, Renaud Lambiotte

Community detection, the decomposition of a graph into essential building blocks, has been a core research topic in network science over the past years.

Social and Information Networks Data Analysis, Statistics and Probability Physics and Society

Cannot find the paper you are looking for? You can Submit a new open access paper.