no code implementations • 17 Jan 2024 • Massimiliano Datres, Gian Paolo Leonardi, Alessio Figalli, David Sutter
We introduce a novel capacity measure 2sED for statistical models based on the effective dimension.
1 code implementation • 29 Nov 2022 • Lénaïc Chizat, Maria Colombo, Xavier Fernández-Real, Alessio Figalli
We finally study the continuous-time limit obtained for infinitely wide linear neural networks and show that the linear predictors of the neural network converge at an exponential rate to the minimal $\ell_2$-norm minimizer of the risk.
1 code implementation • 9 Dec 2021 • Amira Abbas, David Sutter, Alessio Figalli, Stefan Woerner
Making statements about the performance of trained models on tasks involving new data is one of the primary goals of machine learning, i. e., to understand the generalization power of a model.
2 code implementations • 30 Oct 2020 • Amira Abbas, David Sutter, Christa Zoufal, Aurélien Lucchi, Alessio Figalli, Stefan Woerner
We show that quantum neural networks are able to achieve a significantly better effective dimension than comparable classical neural networks.
no code implementations • 29 Jan 2020 • Oksana Berezniuk, Alessio Figalli, Raffaele Ghigliazza, Kharen Musaelian
We introduce a notion of "effective dimension" of a statistical model based on the number of cubes of size $1/\sqrt{n}$ needed to cover the model space when endowed with the Fisher Information Matrix as metric, $n$ being the number of observations.