activity
20142023
most citedHamilton--Jacobi equations for controlled gradient flows: the comparison principle

14 citations · 33 across the 24 of their papers we have counts for

collaborators

32 papers

math.ST2023

KL Convergence Guarantees for Score diffusion models under minimal data assumptions

Giovanni Conforti, Alain Durmus, Marta Gentiloni Silveri

Diffusion models are a new class of generative models that revolve around the estimation of the score function associated with a stochastic differential equation. Subsequent to its…

math.PR2023

Non-asymptotic convergence bounds for Sinkhorn iterates and their gradients: a coupling approach

Giacomo Greco, Maxence Noble, Giovanni Conforti +1

Computational optimal transport (OT) has recently emerged as a powerful framework with applications in various fields. In this paper we focus on a relaxation of the original OT pro…

math.PR2023

Quantitative contraction rates for Sinkhorn's algorithm: beyond bounded costs and compact marginals

Giovanni Conforti, Alain Durmus, Giacomo Greco

We show non-asymptotic exponential convergence of Sinkhorn iterates to the Schrödinger potentials, solutions of the quadratic Entropic Optimal Transport problem on .…

math.AP2023

Hamilton--Jacobi equations for controlled gradient flows: cylindrical test functions

Giovanni Conforti, Richard C. Kraaij, Daniela Tonon

This work is the second part of a program initiated in arXiv:2111.13258 aiming at the development of an intrinsic geometric well-posedness theory for Hamilton-Jacobi equations rela…

math.PR2023

Mean Field Optimization Problem Regularized by Fisher Information

Julien Claisse, Giovanni Conforti, Zhenjie Ren +1

Recently there is a rising interest in the research of mean field optimization, in particular because of its role in analyzing the training of neural networks. In this paper by add…

math.PR2023

Weak semiconvexity estimates for Schrödinger potentials and logarithmic Sobolev inequality for Schrödinger bridges

Giovanni Conforti

We investigate the quadratic Schrödinger bridge problem, a.k.a. Entropic Optimal Transport problem, and obtain weak semiconvexity and semiconcavity bounds on Schrödinger potentials…

math.PR2022★ 2 cited

Gradient estimates for the Schrödinger potentials: convergence to the Brenier map and quantitative stability

Alberto Chiarini, Giovanni Conforti, Giacomo Greco +1

We show convergence of the gradients of the Schrödinger potentials to the Brenier map in the small-time limit under general assumptions on the marginals, which allow for unbounded…

math.AP2021★ 14 cited

Hamilton--Jacobi equations for controlled gradient flows: the comparison principle

Giovanni Conforti, Richard Kraaij, Daniela Tonon

Motivated by recent developments in the fields of large deviations for interacting particle system and mean field control, we establish a comparison principle for the Hamilton--Jac…

math.PR2021

Entropic turnpike estimates for the kinetic Schrödinger problem

Alberto Chiarini, Giovanni Conforti, Giacomo Greco +1

We investigate the kinetic Schrödinger problem, obtained considering Langevin dynamics instead of Brownian motion in Schrödinger's thought experiment. Under a quasilinearity assump…

math.PR2021

Time reversal of Markov processes with jumps under a finite entropy condition

Giovanni Conforti, Christian Léonard

Motivated by entropic optimal transport, time reversal of Markov jump processes in is investigated. Relying on an abstract integration by parts formula for the carré…

math.PR2021★ 1 cited

Time reversal of diffusion processes under a finite entropy condition

Patrick Cattiaux, Giovanni Conforti, Ivan Gentil +1

Motivated by entropic optimal transport, time reversal of diffusion processes is revisited. An integration by parts formula is derived for the carré du champ of a Markov process in…

math.OC2021

A non-linear monotonicity principle and applications to Schrödinger type problems

Julio Backhoff-Veraguas, Mathias Beiglböck, Giovanni Conforti

A basic idea in optimal transport is that optimizers can be characterized through a geometric property of their support sets called cyclical monotonicity. In recent years, similar…

math.CA2020★ 3 cited

On the variational interpretation of local logarithmic Sobolev inequalities

Gauthier Clerc, Giovanni Conforti, Ivan Gentil

The celebrated Otto calculus has established itself as a powerful tool for proving quantitative energy dissipation estimates and provides with an elegant geometric interpretation o…

math.AP2020

Long-time behaviour of entropic interpolations

Gauthier Clerc, Giovanni Conforti, Ivan Gentil

In this article we investigate entropic interpolations. These measure valued curves describe the optimal solutions of the Schr{ö}dinger problem [Sch31], which is the problem of fin…

math.PR2020

A probabilistic approach to convex -entropy decay for Markov chains

Giovanni Conforti

We study the exponential dissipation of entropic functionals for continuous time Markov chains and the associated convex Sobolev inequalities, including MLSI and Beckner inequaliti…

cs.GT2020

Game on Random Environment, Mean-field Langevin System and Neural Networks

Giovanni Conforti, Anna Kazeykina, Zhenjie Ren

In this paper we study a type of games regularized by the relative entropy, where the players' strategies are coupled through a random environment variable. Besides the existence a…

math.PR2019

A formula for the time derivative of the entropic cost and applications

Giovanni Conforti, Luca Tamanini

In the recent years the Schrödinger problem has gained a lot of attention because of the connection, in the small-noise regime, with the Monge-Kantorovich optimal transport problem…

math.PR2019★ 4 cited

The mean field Schrödinger problem: ergodic behavior, entropy estimates and functional inequalities

Julio Backhoff-Veraguas, Giovani Conforti, Ivan Gentil +1

We study the mean field Schrödinger problem (MFSP), that is the problem of finding the most likely evolution of a cloud of interacting Brownian particles conditionally on the obser…

math.OC2019

Multi-marginal Schrodinger bridges

Yongxin Chen, Giovanni Conforti, Tryphon T. Georgiou +1

We consider the problem to identify the most likely flow in phase space, of (inertial) particles under stochastic forcing, that is in agreement with spatial (marginal) distribution…

math.PR2018★ 1 cited

Around the entropic Talagrand inequality

Giovanni Conforti, Luigia Ripani

In this article we study generalization of the classical Talagrand transport-entropy inequality in which the Wasserstein distance is replaced by the entropic transportation cost. T…

math.PR2018

Conditioned point processes with application to Lévy bridges

Giovanni Conforti, Tetiana Kosenkova, Sylvie Roelly

Our first result concerns a characterisation by means of a functional equation of Poisson point processes conditioned by the value of their first moment. It leads to a generalised…

math.OC2018★ 4 cited

Measure-valued spline curves: an optimal transport viewpoint

Yongxin Chen, Giovanni Conforti, Tryphon T. Georgiou

The aim of this article is to introduce and address the problem to smoothly interpolate (empirical) probability measures. To this end, we lift the concept of a spline curve from th…

math-ph2017

Extremal flows on Wasserstein space

Giovanni Conforti, Michele Pavon

We develop an intrinsic geometric approach to calculus of variations on Wasserstein space. We show that the flows associated to the Schroedinger bridge with general prior, to Optim…

math.PR2017★ 2 cited

Approximating conditional distributions

Alberto Chiarini, Alessandra Cipriani, Giovanni Conforti

In this article, we discuss the basic ideas of a general procedure to adapt the Stein-Chen method to bound the distance between conditional distributions. From an integration-by-pa…