Antonio Ocello

According to our database, Antonio Ocello authored at least 8 papers between 2025 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Do Heavy Tails Help Diffusion? On the Subtle Trade-off Between Initialization and Training.

Hamza Cherkaoui, Hélène Halconruy, Antonio Ocello

CoRR, May, 2026

On Forgetting and Stability of Score-based Generative models.

Stanislas Strasman, Gabriel Cardoso, Sylvain Le Corff, Vincent Lemaire, Antonio Ocello

CoRR, January, 2026

2025

Discrete Markov Probabilistic Models.

Le-Tuyet-Nhi Pham, Dario Shariatian, Antonio Ocello, Giovanni Conforti, Alain Durmus

CoRR, February, 2025

An analysis of the noise schedule for score-based generative models.

Stanislas Strasman, Antonio Ocello, Claire Boyer, Sylvain Le Corff, Vincent Lemaire

Trans. Mach. Learn. Res., 2025

Wasserstein Convergence of Critically Damped Langevin Diffusions.

Stanislas Strasman, Sobihan Surendran, Claire Boyer, Sylvain Le Corff, Vincent Lemaire, Antonio Ocello

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Beyond Log-Concavity and Score Regularity: Improved Convergence Bounds for Score-Based Generative Models in W2-distance.

Marta Gentiloni Silveri, Antonio Ocello

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Discrete Markov Probabilistic Models: An Improved Discrete Score-Based Framework with sharp convergence bounds under minimal assumptions.

Le-Tuyet-Nhi Pham, Dario Shariatian, Antonio Ocello, Giovanni Conforti, Alain Oliviero Durmus

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games.

Antonio Ocello, Daniil Tiapkin, Lorenzo Mancini, Mathieu Laurière, Eric Moulines

Proceedings of the Forty-second International Conference on Machine Learning, 2025