Elisabetta Cornacchia

According to our database, Elisabetta Cornacchia authored at least 12 papers between 2020 and 2025.

Collaborative distances:

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

2025

Low-dimensional Functions are Efficiently Learnable under Randomly Biased Distributions.

Elisabetta Cornacchia, Dan Mikulincer, Elchanan Mossel

CoRR, February, 2025

2024

Learning High-Degree Parities: The Crucial Role of the Initialization.

Emmanuel Abbe, Elisabetta Cornacchia, Jan Hazla, Donald Kougang-Yombi

CoRR, 2024

2023

Learning curves for the multi-class teacher-student perceptron.

Elisabetta Cornacchia, Francesca Mignacco, Rodrigo Veiga, Cédric Gerbelot, Bruno Loureiro, Lenka Zdeborová

Mach. Learn. Sci. Technol., March, 2023

Theory and applications of the Sum-Of-Squares technique.

Francis R. Bach, Elisabetta Cornacchia, Luca Pesce, Giovanni Piccioli

CoRR, 2023

A Mathematical Model for Curriculum Learning.

Elisabetta Cornacchia, Elchanan Mossel

CoRR, 2023

Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs.

Emmanuel Abbe, Elisabetta Cornacchia, Aryo Lotfi

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

A Mathematical Model for Curriculum Learning for Parities.

Elisabetta Cornacchia, Elchanan Mossel

Proceedings of the International Conference on Machine Learning, 2023

2022

Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures.

Emmanuel Abbe, Samy Bengio, Elisabetta Cornacchia, Jon M. Kleinberg, Aryo Lotfi, Maithra Raghu, Chiyuan Zhang

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

An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn.

Emmanuel Abbe, Elisabetta Cornacchia, Jan Hazla, Christopher Marquis

Proceedings of the International Conference on Machine Learning, 2022

2021

Regularization by Misclassification in ReLU Neural Networks.

Elisabetta Cornacchia, Jan Hazla, Ido Nachum, Amir Yehudayoff

CoRR, 2021

Stochastic block model entropy and broadcasting on trees with survey.

Emmanuel Abbe, Elisabetta Cornacchia, Yuzhou Gu, Yury Polyanskiy

Proceedings of the Conference on Learning Theory, 2021

2020

Polarization in Attraction-Repulsion Models.

Elisabetta Cornacchia, Neta Singer, Emmanuel Abbe

Proceedings of the IEEE International Symposium on Information Theory, 2020