activity
20242026
most citedThermodynamic Geometric Constraint on the Spectrum of Markov Rate Matrices

1 citations · 1 across the 2 of their papers we have counts for

collaborators

6 papers

cs.LG2026

Random Wavelet Features for Graph Kernel Machines

Valentin de Bassompierre, Jean-Charles Delvenne, Laurent Jacques

Node embeddings map graph vertices into low-dimensional Euclidean spaces while preserving structural information. They are central to tasks such as node classification, link predic…

cond-mat.stat-mech20251 cited

Thermodynamic Geometric Constraint on the Spectrum of Markov Rate Matrices

Guo-Hua Xu, Artemy Kolchinsky, Jean-Charles Delvenne +1

The spectrum of Markov generators encodes physical information beyond simple decay and oscillation, which reflects irreversibility and governs the structure of correlation function…

math-ph2025

Analog and Symbolic Computation through the Koopman Framework

Francesco Caravelli, Jean-Charles Delvenne

We develop a Koopman operator framework for studying the {computational properties} of dynamical systems. Specifically, we show that the resolvent of the Koopman operator provides…

cond-mat.stat-mech2025

Noise-dissipation relation for nonlinear electronic circuits

Léopold Van Brandt, Jean-Charles Delvenne

An extension of fluctuation-dissipation theorem is used to derive a "speed limit" theorem for nonlinear electronic devices. This speed limit provides a lower bound on the dissipati…

cs.LG2025

Theoretical Barriers in Bellman-Based Reinforcement Learning

Brieuc Pinon, Raphaël Jungers, Jean-Charles Delvenne

Reinforcement Learning algorithms designed for high-dimensional spaces often enforce the Bellman equation on a sampled subset of states, relying on generalization to propagate know…

cond-mat.stat-mech2024

Predicting State Transitions in Autonomous Nonlinear Bistable Systems with Hidden Stochasticity

Léopold Van Brandt, Jean-Charles Delvenne

Bistable autonomous systems can be found inmany areas of science. When the intrinsic noise intensity is large, these systems exhibits stochastic transitions from onemetastable stea…