743 citations · 1.4k across the 18 of their papers we have counts for
4 papers · 1 filter
Conditioned Text Generation with Transfer for Closed-Domain 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…
Align, then memorise: the dynamics of learning with feedback alignment
Maria Refinetti, Stéphane d'Ascoli, Ruben Ohana +1
Direct Feedback Alignment (DFA) is emerging as an efficient and biologically plausible alternative to the ubiquitous backpropagation algorithm for training deep neural networks. De…
Triple descent and the two kinds of overfitting: Where & why do they appear?
Stéphane d'Ascoli, Levent Sagun, Giulio Biroli
A recent line of research has highlighted the existence of a "double descent" phenomenon in deep learning, whereby increasing the number of training examples causes the general…
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…