activity
20182023
most citedDouble Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime

52 citations · 69 across the 6 of their papers we have counts for

collaborators
Showing cs.LGShow all

9 papers · 1 filter

cs.LG2023

Boolformer: Symbolic Regression of Logic Functions with Transformers

Stéphane d'Ascoli, Arthur Renard, Vassilis Papadopoulos +3

We introduce Boolformer, a Transformer-based model trained to perform end-to-end symbolic regression of Boolean functions. First, we show that it can predict compact formulas for c…

cs.LG2023

Length Generalization in Arithmetic Transformers

Samy Jelassi, Stéphane d'Ascoli, Carles Domingo-Enrich +3

We examine how transformers cope with two challenges: learning basic integer arithmetic, and generalizing to longer sequences than seen during training. We find that relative posit…

cs.LG20229 cited

End-to-end symbolic regression with transformers

Pierre-Alexandre Kamienny, Stéphane d'Ascoli, Guillaume Lample +1

Symbolic regression, the task of predicting the mathematical expression of a function from the observation of its values, is a difficult task which usually involves a two-step proc…

cs.LG20224 cited

Optimal learning rate schedules in high-dimensional non-convex optimization problems

Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli

Learning rate schedules are ubiquitously used to speed up and improve optimisation. Many different policies have been introduced on an empirical basis, and theoretical analyses hav…

cs.LG20213 cited

Transformed CNNs: recasting pre-trained convolutional layers with self-attention

Stéphane d'Ascoli, Levent Sagun, Giulio Biroli +1

Vision Transformers (ViT) have recently emerged as a powerful alternative to convolutional networks (CNNs). Although hybrid models attempt to bridge the gap between these two archi…

cs.LG2021

On the interplay between data structure and loss function in classification problems

Stéphane d'Ascoli, Marylou Gabrié, Levent Sagun +1

One of the central puzzles in modern machine learning is the ability of heavily overparametrized models to generalize well. Although the low-dimensional structure of typical datase…