This seminar aims to increase the links between the different laboratories in Saclay in the field of Applied Maths, Statistics and Machine Learning. The Seminar is organized every first Tuesday of the month with 2 presentations followed by a small refreshment. The localization of the seminar will change to accommodate the different labs.
Organization
Due to access restriction, you need to register for the seminar. A link is provided in the description and should also be sent with the seminar announcement. It will also help us organize for the food quantities. If you think you will come, please register! (even if you are unsure)
To not miss the next seminar, please subscribe to the announcement mailing list palaisien@inria.fr.
You can also add the calendar from the seminar to your own calendar (see below).
Next seminars
REGISTER
03 Mar 2026, 12h At Inria Saclay - Amphi Sophie Germain
Antonio Ocello-Convergence Guarantees for Score-Based Generative Models: From Continuous Diffusions to Discrete Data
Score-based generative models, also known as diffusion models, can be naturally formulated in continuous time as the time-reversal of a stochastic differential equation. In this talk, we present this formalism and highlight its connection with stochastic optimal control, where generation is interpreted as steering a reference diffusion toward a target distribution. Within this framework, we discuss the convergence bounds established by Conforti, Durmus, and ...
Score-based generative models, also known as diffusion models, can be naturally formulated in continuous time as the time-reversal of a stochastic differential equation. In this talk, we present this formalism and highlight its connection with stochastic optimal control, where generation is interpreted as steering a reference diffusion toward a target distribution. Within this framework, we discuss the convergence bounds established by Conforti, Durmus, and Gentiloni-Silveri (2025, SIAM Journal on Mathematics of Data Science), providing non-asymptotic guarantees under minimal regularity assumptions.
We then extend this perspective to discrete data generation via Discrete Markov Probabilistic Models (DMPMs). Here, the forward process is a continuous-time Markov chain on discrete states, and the reverse-time jump intensity is governed by a discrete analogue of the score function, characterized as a conditional expectation of the forward process. We present convergence guarantees in this discrete setting and illustrate their effectiveness on Bernoulli and binary MNIST data. This unified view connects diffusion models, optimal control, and discrete generative modeling within a rigorous convergence framework. This talk is based on joint work with Le-Tuyet-Nhi Pham, Dario Shariatian, Giovanni Conforti, and Alain Oliviero Durmus (ICML 2025 ).
Charlotte Laclau-There is No Universal Fairness: Lessons from Text Classification to Graph Prediction
Despite extensive research on algorithmic fairness, its adoption in real-world systems remains limited. Drawing on case studies in text classification and graph link prediction, I argue that fairness interventions are inherently context-dependent and rarely transfer across application domains. In particular, structural constraints in graphs and the use of pre-trained models in NLP challenge standard fairness assumptions. Beyond these domain-specific limitations, sensitive attributes are often...
Despite extensive research on algorithmic fairness, its adoption in real-world systems remains limited. Drawing on case studies in text classification and graph link prediction, I argue that fairness interventions are inherently context-dependent and rarely transfer across application domains. In particular, structural constraints in graphs and the use of pre-trained models in NLP challenge standard fairness assumptions. Beyond these domain-specific limitations, sensitive attributes are often partially observed or entirely unavailable, and static fairness analyses overlook the long-term feedback effects induced by deployed systems. I'll conclude with reflections on the implications of this context-dependence for both researchers and practitioners.
REGISTER
07 Apr 2026, 12h At Inria Saclay - Amphi Sophie Germain
Scientific Committee
The program and the organization of this seminar is driven by a scientific committee composed of members of the different laboratories in Saclay. The members of the committee are currently:
