52 citations · 53 across the 2 of their papers we have counts for
4 papers
Double Trouble in Double Descent : Bias and Variance(s) in the Lazy Regime
Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli +1
Deep neural networks can achieve remarkable generalization performances while interpolating the training data perfectly. Rather than the U-curve emblematic of the bias-variance tra…
Conditioned Query Generation for Task-Oriented Dialogue Systems
Stéphane d'Ascoli, Alice Coucke, Francesco Caltagirone +2
Scarcity of training data for task-oriented dialogue systems is a well known problem that is usually tackled with costly and time-consuming manual data annotation. An alternative s…
Finding the Needle in the Haystack with Convolutions: on the benefits of architectural bias
Stéphane d'Ascoli, Levent Sagun, Joan Bruna +1
Despite the phenomenal success of deep neural networks in a broad range of learning tasks, there is a lack of theory to understand the way they work. In particular, Convolutional N…
Scaling description of generalization with number of parameters in deep learning
Mario Geiger, Arthur Jacot, Stefano Spigler +6
Supervised deep learning involves the training of neural networks with a large number of parameters. For large enough , in the so-called over-parametrized regime, one can es…