Publication
Representer Theorems for Sparsity-Promoting $ ℓ _{ 1 } $ Regularization
Publications associées (50)
High-Dimensional Kernel Methods under Covariate Shift: Data-Dependent Implicit Regularization
This paper studies kernel ridge regression in high dimensions under covariate shifts and analyzes the role of importance re-weighting. We first derive the asymptotic expansion of high dimensional kernels under covariate shifts. By a bias-variance decomposi ...
2024On the fast assemblage of finite element matrices with application to nonlinear heat transfer problems
The finite element method is a well-established method for the numerical solution of partial differential equations (PDEs), both linear and nonlinear. However, the repeated re -assemblage of finite element matrices for nonlinear PDEs is frequently pointed ...
ELSEVIER SCIENCE INC2023A model for the consolidation of hybrid textiles considering air entrapment, dissolution and diffusion
Véronique Michaud, Vincent Werlen, Christian Rytka
A new model is proposed for the consolidation of hybrid textiles, in which air entrapment and dissolution are considered. One of the key parameters is tow permeability, which is described by the analytical model of Gebart and validated at very high fibre v ...
ELSEVIER SCI LTD2023Biobased surfactants
Jeremy Luterbacher, Songlan Sun, Stefania Bertella, Anastasiia Komarova
Compound of the general formula (Ia), (Ib) and (Ic) R50 and R60 are different form each other and are selected from the group consisting of -R70, -ZR70, -Z-OH, -Z-NH2, -Z-SH, -Z-OC(O)R70, -OC(O)R70, - COOH and its corresponding salts, -C(O)NH2, -C(O)NH-R70 ...
2023(S)GD over Diagonal Linear Networks: Implicit Regularisation, Large Stepsizes and Edge of Stability
Nicolas Henri Bernard Flammarion, Scott William Pesme, Mathieu Even
In this paper, we investigate the impact of stochasticity and large stepsizes on the implicit regularisation of gradient descent (GD) and stochastic gradient descent (SGD) over diagonal linear networks. We prove the convergence of GD and SGD with macroscop ...
2023Saddle-to-Saddle Dynamics in Diagonal Linear Networks
Nicolas Henri Bernard Flammarion, Scott William Pesme
In this paper we fully describe the trajectory of gradient flow over diagonal linear networks in the limit of vanishing initialisation. We show that the limiting flow successively jumps from a saddle of the training loss to another until reaching the minim ...
2023System and method for transcoding spectral data with task-based optimization via symmetric non-negative matrix factorization
A computer-implemented method for reconstructing/recovering high-resolution visible light spectral data at a target resolution d, that comprises obtaining a configuration of a low- resolution multi-channel imaging sensor of resolution p, the configuration ...
2022Geodesic Distance on Optimally Regularized Functional Connectomes Uncovers Individual Fingerprints
Background: Functional connectomes (FCs) have been shown to provide a reproducible individual fingerprint, which has opened the possibility of personalized medicine for neuro/psychiatric disorders. Thus, developing accurate ways to compare FCs is essential ...
MARY ANN LIEBERT, INC2021Efficient Learning of a Linear Dynamical System with Stability Guarantees
Daniel Kuhn, Wouter Jongeneel, Tobias Sutter
We propose a principled method for projecting an arbitrary square matrix to the non- convex set of asymptotically stable matrices. Leveraging ideas from large deviations theory, we show that this projection is optimal in an information-theoretic sense and ...
2021New Results in Integer and Lattice Programming
An integer program (IP) is a problem of the form , where , , , and is a separable convex objective function.
The problem o ...
EPFL2020