Stefano Sarao Mannelli

According to our database, Stefano Sarao Mannelli authored at least 30 papers between 2018 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of three.

2026

The Interplay of Data Structure and Imbalance in the Learning Dynamics of Diffusion Models.

Flavio Nicoletti, Chenxiao Ma, Enrico Ventura, Luca Saglietti, Stefano Sarao Mannelli

CoRR, May, 2026

Position: the Stochastic Parrot in the Coal Mine. Model Collapse is a Threat to Low-Resource Communities.

Devon Jarvis, Richard Klein, Benjamin Rosman, Steven James, Stefano Sarao Mannelli

CoRR, May, 2026

Sharp description of local minima in the loss landscape of high-dimensional two-layer ReLU neural networks.

Jie Huang, Bruno Loureiro, Stefano Sarao Mannelli

CoRR, April, 2026

2025

Optimal Protocols for Continual Learning via Statistical Physics and Control Theory.

Francesco Mori, Stefano Sarao Mannelli, Francesca Mignacco

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

A Theory of Initialisation's Impact on Specialisation.

Devon Jarvis, Sebastian Lee, Clémentine Carla Juliette Dominé, Andrew M. Saxe, Stefano Sarao Mannelli

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Curriculum learning in humans and neural networks.

Younes Strittmatter, Stefano Sarao Mannelli, Miguel Ruiz-Garcia, Sebastian Musslick, Markus Spitzer

Proceedings of the 47th Annual Meeting of the Cognitive Science Society, 2025

2024

How to choose the right transfer learning protocol? A qualitative analysis in a controlled set-up.

Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio

Trans. Mach. Learn. Res., 2024

Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training.

Anchit Jain, Rozhin Nobahari, Aristide Baratin, Stefano Sarao Mannelli

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks.

Stefano Sarao Mannelli, Yaraslau Ivashinka, Andrew M. Saxe, Luca Saglietti

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning.

Jin Hwa Lee, Stefano Sarao Mannelli, Andrew M. Saxe

Proceedings of the Forty-first International Conference on Machine Learning, 2024

A meta-learning framework for rationalizing cognitive fatigue in neural systems.

Yujun Li, Rodrigo Carrasco-Davis, Younes Strittmatter, Stefano Sarao Mannelli, Sebastian Musslick

Proceedings of the 46th Annual Meeting of the Cognitive Science Society, 2024

2023

The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions.

Nishil Patel, Sebastian Lee, Stefano Sarao Mannelli, Sebastian Goldt, Andrew M. Saxe

CoRR, 2023

Optimal transfer protocol by incremental layer defrosting.

Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio

CoRR, 2023

2022

Probing transfer learning with a model of synthetic correlated datasets.

Federica Gerace, Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe, Lenka Zdeborová

Mach. Learn. Sci. Technol., 2022

Inducing bias is simpler than you think.

Stefano Sarao Mannelli, Federica Gerace, Negar Rostamzadeh, Luca Saglietti

CoRR, 2022

An Analytical Theory of Curriculum Learning in Teacher-Student Networks.

Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation.

Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew M. Saxe

Proceedings of the International Conference on Machine Learning, 2022

2021

Just a Momentum: Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problem.

Stefano Sarao Mannelli, Pierfrancesco Urbani

CoRR, 2021

Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems.

Stefano Sarao Mannelli, Pierfrancesco Urbani

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

2020

Epidemic mitigation by statistical inference from contact tracing data.

Antoine Baker, Indaco Biazzo, Alfredo Braunstein, Giovanni Catania, Luca Dall'Asta, Alessandro Ingrosso, Florent Krzakala, Fabio Mazza, Marc Mézard, Anna Paola Muntoni, Maria Refinetti, Stefano Sarao Mannelli, Lenka Zdeborová

CoRR, 2020

Post-Workshop Report on Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver.

Levent Sagun, Çaglar Gülçehre, Adriana Romero, Negar Rostamzadeh, Stefano Sarao Mannelli

CoRR, 2020

Winning the competition: enhancing counter-contagion in SIS-like epidemic processes.

Argyris Kalogeratos, Stefano Sarao Mannelli

CoRR, 2020

Thresholds of descending algorithms in inference problems.

Stefano Sarao Mannelli, Lenka Zdeborová

CoRR, 2020

Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions.

Stefano Sarao Mannelli, Eric Vanden-Eijnden, Lenka Zdeborová

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval.

Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

2019

Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model.

Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Lenka Zdeborová

CoRR, 2019

Passed & Spurious: analysing descent algorithms and local minima in spiked matrix-tensor model.

Stefano Sarao Mannelli, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová

CoRR, 2019

Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models.

Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Lenka Zdeborová

Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models.

Stefano Sarao Mannelli, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová

Proceedings of the 36th International Conference on Machine Learning, 2019

2018

Marvels and Pitfalls of the Langevin Algorithm in Noisy High-dimensional Inference.

Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová

CoRR, 2018