Picture for Emmanuel Abbe

Emmanuel Abbe

Generalization on the Unseen, Logic Reasoning and Degree Curriculum

Jan 30, 2023
Emmanuel Abbe, Samy Bengio, Aryo Lotfi, Kevin Rizk

Figure 1 for Generalization on the Unseen, Logic Reasoning and Degree Curriculum

Figure 2 for Generalization on the Unseen, Logic Reasoning and Degree Curriculum

Figure 3 for Generalization on the Unseen, Logic Reasoning and Degree Curriculum

Figure 4 for Generalization on the Unseen, Logic Reasoning and Degree Curriculum

* 37 pages, 10 figures

Access Paper or Ask Questions

On the non-universality of deep learning: quantifying the cost of symmetry

Aug 05, 2022
Emmanuel Abbe, Enric Boix-Adsera

Figure 1 for On the non-universality of deep learning: quantifying the cost of symmetry

Figure 2 for On the non-universality of deep learning: quantifying the cost of symmetry

Figure 3 for On the non-universality of deep learning: quantifying the cost of symmetry

Access Paper or Ask Questions

An initial alignment between neural network and target is needed for gradient descent to learn

Feb 25, 2022
Emmanuel Abbe, Elisabetta Cornacchia, Jan Hązła, Christopher Marquis

Figure 1 for An initial alignment between neural network and target is needed for gradient descent to learn

Figure 2 for An initial alignment between neural network and target is needed for gradient descent to learn

Access Paper or Ask Questions

Binary perceptron: efficient algorithms can find solutions in a rare well-connected cluster

Nov 04, 2021
Emmanuel Abbe, Shuangping Li, Allan Sly

Figure 1 for Binary perceptron: efficient algorithms can find solutions in a rare well-connected cluster

Figure 2 for Binary perceptron: efficient algorithms can find solutions in a rare well-connected cluster

Figure 3 for Binary perceptron: efficient algorithms can find solutions in a rare well-connected cluster

Access Paper or Ask Questions

On the Power of Differentiable Learning versus PAC and SQ Learning

Aug 09, 2021
Emmanuel Abbe, Pritish Kamath, Eran Malach, Colin Sandon, Nathan Srebro

Figure 1 for On the Power of Differentiable Learning versus PAC and SQ Learning

Access Paper or Ask Questions