10 papers
Trajectory inference via Acceleration Matching
Bartolo Dazzini, Giovanni Conforti, Alain Durmus +1
Trajectory inference is a fundamental problem in many scientific domains: given a collection of unpaired snapshots of observations at discrete time points, the goal is to generate…
Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees
Marta Gentiloni Silveri, Giovanni Conforti, Alain Durmus
Diffusion Flow Matching (DFM) has recently emerged as a versatile framework for generative modeling, yet its theoretical convergence properties remain only partially understood. In…
Iterative Tilting for Diffusion Fine-Tuning
Jean Pachebat, Giovanni Conforti, Alain Durmus +1
We introduce iterative tilting, a gradient-free method for fine-tuning diffusion models toward reward-tilted distributions. The method decomposes a large reward tilt int…
Non-Asymptotic Convergence of Discrete Diffusion Models: Masked and Random Walk dynamics
Giovanni Conforti, Alain Durmus, Le-Tuyet-Nhi Pham +1
Diffusion models for continuous state spaces based on Gaussian noising processes are now relatively well understood from both practical and theoretical perspectives. In contrast, r…
Exponential Convergence Guarantees for Iterative Markovian Fitting
Marta Gentiloni Silveri, Giovanni Conforti, Alain Durmus
The Schrödinger Bridge (SB) problem has become a fundamental tool in computational optimal transport and generative modeling. To address this problem, ideal methods such as Iterati…
A coupling approach to Lipschitz transport maps
Giovanni Conforti, Katharina Eichinger
In this note, we propose a probabilistic approach to bound the (dimension-free) Lipschitz constant of the Langevin flow map on introduced by Kim and Milman (2012). A…
Bit-Level Discrete Diffusion with Markov Probabilistic Models: An Improved Framework with Sharp Convergence Bounds under Minimal Assumptions
Le-Tuyet-Nhi Pham, Dario Shariatian, Antonio Ocello +2
This paper introduces Discrete Markov Probabilistic Models (DMPMs), a novel discrete diffusion algorithm for discrete data generation. The algorithm operates in discrete bit space,…
The exponential turnpike phenomenon for mean field game systems: weakly monotone drifts and small interactions
Alekos Cecchin, Giovanni Conforti, Alain Durmus +1
This article aims at quantifying the long time behavior of solutions of mean field PDE systems arising in the theory of Mean Field Games and McKean-Vlasov control. Our main contrib…
Theoretical guarantees in KL for Diffusion Flow Matching
Marta Gentiloni Silveri, Giovanni Conforti, Alain Durmus
Flow Matching (FM) (also referred to as stochastic interpolants or rectified flows) stands out as a class of generative models that aims to bridge in finite time the target distrib…
Projected Langevin dynamics and a gradient flow for entropic optimal transport
Giovanni Conforti, Daniel Lacker, Soumik Pal
The classical (overdamped) Langevin dynamics provide a natural algorithm for sampling from its invariant measure, which uniquely minimizes an energy functional over the space of pr…