Stefano Sarao Mannelli

36 papers A* 12B 2Journal 22

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	A Theory of Initialisation's Impact on Specialisation. ICLR Devon Jarvis, Sebastian Lee, Clémentine Carla Juliette Dominé, Andrew M. Saxe, Stefano Sarao Mannelli
2025	J	`jnl`	A Theory of Initialisation's Impact on Specialisation. CoRR Devon Jarvis, Sebastian Lee, Clémentine C. J. Dominé, Andrew M. Saxe, Stefano Sarao Mannelli
2025	B	`conf`	Curriculum learning in humans and neural networks. CogSci Younes Strittmatter, Stefano Sarao Mannelli, Miguel Ruiz-Garcia, Sebastian Musslick, Markus Spitzer
2025	A*	`conf`	Optimal Protocols for Continual Learning via Statistical Physics and Control Theory. ICLR Francesco Mori, Stefano Sarao Mannelli, Francesca Mignacco
2024	B	`conf`	A meta-learning framework for rationalizing cognitive fatigue in neural systems. CogSci Yujun Li, Rodrigo Carrasco-Davis, Younes Strittmatter, Stefano Sarao Mannelli, Sebastian Musslick
2024	A*	`conf`	Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training. NeurIPS Anchit Jain, Rozhin Nobahari, Aristide Baratin, Stefano Sarao Mannelli
2024	J	`jnl`	Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training. CoRR Anchit Jain, Rozhin Nobahari, Aristide Baratin, Stefano Sarao Mannelli
2024	J	`jnl`	How to choose the right transfer learning protocol? A qualitative analysis in a controlled set-up. Trans. Mach. Learn. Res. Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio
2024	J	`jnl`	Optimal Protocols for Continual Learning via Statistical Physics and Control Theory. CoRR Francesco Mori, Stefano Sarao Mannelli, Francesca Mignacco
2024	A*	`conf`	Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks. ICML Stefano Sarao Mannelli, Yaraslau Ivashinka, Andrew M. Saxe, Luca Saglietti
2024	J	`jnl`	Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks. CoRR Stefano Sarao Mannelli, Yaraslau Ivashinka, Andrew M. Saxe, Luca Saglietti
2024	A*	`conf`	Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning. ICML Jin Hwa Lee, Stefano Sarao Mannelli, Andrew M. Saxe
2023	J	`jnl`	Optimal transfer protocol by incremental layer defrosting. CoRR Federica Gerace, Diego Doimo, Stefano Sarao Mannelli, Luca Saglietti, Alessandro Laio
2023	J	`jnl`	The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions. CoRR Nishil Patel, Sebastian Lee, Stefano Sarao Mannelli, Sebastian Goldt, Andrew M. Saxe
2022	A*	`conf`	An Analytical Theory of Curriculum Learning in Teacher-Student Networks. NeurIPS Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe
2022	J	`jnl`	Inducing bias is simpler than you think. CoRR Stefano Sarao Mannelli, Federica Gerace, Negar Rostamzadeh, Luca Saglietti
2022	J	`jnl`	Maslow's Hammer for Catastrophic Forgetting: Node Re-Use vs Node Activation. CoRR Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew M. Saxe
2022	A*	`conf`	Maslow's Hammer in Catastrophic Forgetting: Node Re-Use vs. Node Activation. ICML Sebastian Lee, Stefano Sarao Mannelli, Claudia Clopath, Sebastian Goldt, Andrew M. Saxe
2022	J	`jnl`	Probing transfer learning with a model of synthetic correlated datasets. Mach. Learn. Sci. Technol. Federica Gerace, Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe, Lenka Zdeborová
2021	J	`jnl`	An Analytical Theory of Curriculum Learning in Teacher-Student Networks. CoRR Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe
2021	A*	`conf`	Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problems. NeurIPS Stefano Sarao Mannelli, Pierfrancesco Urbani
2021	J	`jnl`	Just a Momentum: Analytical Study of Momentum-Based Acceleration Methods in Paradigmatic High-Dimensional Non-Convex Problem. CoRR Stefano Sarao Mannelli, Pierfrancesco Urbani
2021	J	`jnl`	Probing transfer learning with a model of synthetic correlated datasets. CoRR Federica Gerace, Luca Saglietti, Stefano Sarao Mannelli, Andrew M. Saxe, Lenka Zdeborová
2020	A*	`conf`	Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval. NeurIPS Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
2020	J	`jnl`	Complex Dynamics in Simple Neural Networks: Understanding Gradient Flow in Phase Retrieval. CoRR Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
2020	J	`jnl`	Epidemic mitigation by statistical inference from contact tracing data. CoRR 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
2020	A*	`conf`	Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions. NeurIPS Stefano Sarao Mannelli, Eric Vanden-Eijnden, Lenka Zdeborová
2020	J	`jnl`	Optimization and Generalization of Shallow Neural Networks with Quadratic Activation Functions. CoRR Stefano Sarao Mannelli, Eric Vanden-Eijnden, Lenka Zdeborová
2020	J	`jnl`	Post-Workshop Report on Science meets Engineering in Deep Learning, NeurIPS 2019, Vancouver. CoRR Levent Sagun, Çaglar Gülçehre, Adriana Romero, Negar Rostamzadeh, Stefano Sarao Mannelli
2020	J	`jnl`	Thresholds of descending algorithms in inference problems. CoRR Stefano Sarao Mannelli, Lenka Zdeborová
2020	J	`jnl`	Winning the competition: enhancing counter-contagion in SIS-like epidemic processes. CoRR Argyris Kalogeratos, Stefano Sarao Mannelli
2019	A*	`conf`	Passed & Spurious: Descent Algorithms and Local Minima in Spiked Matrix-Tensor Models. ICML Stefano Sarao Mannelli, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
2019	J	`jnl`	Passed & Spurious: analysing descent algorithms and local minima in spiked matrix-tensor model. CoRR Stefano Sarao Mannelli, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová
2019	J	`jnl`	Who is Afraid of Big Bad Minima? Analysis of Gradient-Flow in a Spiked Matrix-Tensor Model. CoRR Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Lenka Zdeborová
2019	A*	`conf`	Who is Afraid of Big Bad Minima? Analysis of gradient-flow in spiked matrix-tensor models. NeurIPS Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Lenka Zdeborová
2018	J	`jnl`	Marvels and Pitfalls of the Langevin Algorithm in Noisy High-dimensional Inference. CoRR Stefano Sarao Mannelli, Giulio Biroli, Chiara Cammarota, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová