activity
20152021
most citedKernel Alignment Risk Estimator: Risk Prediction from Training Data

23 citations · 25 across the 5 of their papers we have counts for

collaborators

9 papers

math-ph2021

Asymptotic symmetry and asymptotic solutions to Ito stochastic differential equations

Giuseppe Gaeta, Roman Kozlov, Francesco Spadaro

We consider several aspects of conjugating symmetry methods, including the method of invariants, with an asymptotic approach. In particular we consider how to extend to the stochas…

cs.LG2021

Geometry of the Loss Landscape in Overparameterized Neural Networks: Symmetries and Invariances

Berfin Şimşek, François Ged, Arthur Jacot +4

We study how permutation symmetries in overparameterized multi-layer neural networks generate `symmetry-induced' critical points. Assuming a network with layers of minimal wi…

stat.ML202023 cited

Kernel Alignment Risk Estimator: Risk Prediction from Training Data

Arthur Jacot, Berfin Şimşek, Francesco Spadaro +2

We study the risk (i.e. generalization error) of Kernel Ridge Regression (KRR) for a kernel with ridge and i.i.d. observations. For this, we introduce two objects: the Si…

math-ph2020

On the construction of discrete fermions in the FK-Ising model

Francesco Spadaro

We consider many-point correlation functions of discrete fermions in the two-dimensional FK-Ising model and show that, despite not being commuting observable, they can be realized…

math-ph2020

Symmetry classification of scalar Ito equations with multiplicative noise

Giuseppe Gaeta, Francesco Spadaro

We provide a symmetry classification of scalar stochastic equations with multiplicative noise. These equations can be integrated by means of the Kozlov procedure, by passing to sym…

stat.ML2020

Implicit Regularization of Random Feature Models

Arthur Jacot, Berfin Şimşek, Francesco Spadaro +2

Random Feature (RF) models are used as efficient parametric approximations of kernel methods. We investigate, by means of random matrix theory, the connection between Gaussian RF m…