Search Results for author: Hachem Kadri

Found 26 papers, 3 papers with code

$C^*$-Algebraic Machine Learning: Moving in a New Direction

no code implementations4 Feb 2024 Yuka Hashimoto, Masahiro Ikeda, Hachem Kadri

Machine learning has a long collaborative tradition with several fields of mathematics, such as statistics, probability and linear algebra.

Orthogonal Random Features: Explicit Forms and Sharp Inequalities

no code implementations11 Oct 2023 Nizar Demni, Hachem Kadri

Random features have been introduced to scale up kernel methods via randomization techniques.

Large-Scale Quantum Separability Through a Reproducible Machine Learning Lens

no code implementations15 Jun 2023 Balthazar Casalé, Giuseppe Di Molfetta, Sandrine Anthoine, Hachem Kadri

The quantum separability problem consists in deciding whether a bipartite density matrix is entangled or separable.


Learning in RKHM: a $C^*$-Algebraic Twist for Kernel Machines

no code implementations21 Oct 2022 Yuka Hashimoto, Masahiro Ikeda, Hachem Kadri

Supervised learning in reproducing kernel Hilbert space (RKHS) and vector-valued RKHS (vvRKHS) has been investigated for more than 30 years.

Learning primal-dual sparse kernel machines

1 code implementation27 Aug 2021 Riikka Huusari, Sahely Bhadra, Cécile Capponi, Hachem Kadri, Juho Rousu

In this paper, instead of using the traditional representer theorem, we propose to search for a solution in RKHS that has a pre-image decomposition in the original data space, where the elements don't necessarily correspond to the elements in the training set.

Quantum Perceptron Revisited: Computational-Statistical Tradeoffs

1 code implementation4 Jun 2021 Mathieu Roget, Giuseppe Di Molfetta, Hachem Kadri

Quantum machine learning algorithms could provide significant speed-ups over their classical counterparts; however, whether they could also achieve good generalization remains unclear.

Quantum Machine Learning

Implicit Regularization in Deep Tensor Factorization

no code implementations4 May 2021 Paolo Milanesi, Hachem Kadri, Stéphane Ayache, Thierry Artières

Attempts of studying implicit regularization associated to gradient descent (GD) have identified matrix completion as a suitable test-bed.

Matrix Completion

Entangled Kernels -- Beyond Separability

no code implementations14 Jan 2021 Riikka Huusari, Hachem Kadri

We consider the problem of operator-valued kernel learning and investigate the possibility of going beyond the well-known separable kernels.

Supervised dimensionality reduction

Sparse matrix products for neural network compression

no code implementations1 Jan 2021 Luc Giffon, Hachem Kadri, Stephane Ayache, Ronan Sicre, Thierry Artieres

Over-parameterization of neural networks is a well known issue that comes along with their great performance.

Neural Network Compression

Partial Trace Regression and Low-Rank Kraus Decomposition

1 code implementation ICML 2020 Hachem Kadri, Stéphane Ayache, Riikka Huusari, Alain Rakotomamonjy, Liva Ralaivola

The trace regression model, a direct extension of the well-studied linear regression model, allows one to map matrices to real-valued outputs.

Matrix Completion regression

Mapping individual differences in cortical architecture using multi-view representation learning

no code implementations1 Apr 2020 Akrem Sellami, François-Xavier Dupé, Bastien Cagna, Hachem Kadri, Stéphane Ayache, Thierry Artières, Sylvain Takerkart

In neuroscience, understanding inter-individual differences has recently emerged as a major challenge, for which functional magnetic resonance imaging (fMRI) has proven invaluable.

Representation Learning

Quantum Bandits

no code implementations15 Feb 2020 Balthazar Casalé, Giuseppe Di Molfetta, Hachem Kadri, Liva Ralaivola

We consider the quantum version of the bandit problem known as {\em best arm identification} (BAI).

Deep Networks with Adaptive Nyström Approximation

no code implementations29 Nov 2019 Luc Giffon, Stéphane Ayache, Thierry Artières, Hachem Kadri

Recent work has focused on combining kernel methods and deep learning to exploit the best of the two approaches.

Cross-view kernel transfer

no code implementations14 Oct 2019 Riikka Huusari, Cécile Capponi, Paul Villoutreix, Hachem Kadri

We consider the kernel completion problem with the presence of multiple views in the data.

QuicK-means: Acceleration of K-means by learning a fast transform

no code implementations23 Aug 2019 Luc Giffon, Valentin Emiya, Liva Ralaivola, Hachem Kadri

K-means -- and the celebrated Lloyd algorithm -- is more than the clustering method it was originally designed to be.

Clustering Data Compression

Multi-view Metric Learning in Vector-valued Kernel Spaces

no code implementations21 Mar 2018 Riikka Huusari, Hachem Kadri, Cécile Capponi

We consider the problem of metric learning for multi-view data and present a novel method for learning within-view as well as between-view metrics in vector-valued kernel spaces, as a way to capture multi-modal structure of the data.

Metric Learning

Low-Rank Regression with Tensor Responses

no code implementations NeurIPS 2016 Guillaume Rabusseau, Hachem Kadri

This paper proposes an efficient algorithm (HOLRR) to handle regression tasks where the outputs have a tensor structure.


Higher-Order Low-Rank Regression

no code implementations22 Feb 2016 Guillaume Rabusseau, Hachem Kadri

This paper proposes an efficient algorithm (HOLRR) to handle regression tasks where the outputs have a tensor structure.


Operator-valued Kernels for Learning from Functional Response Data

no code implementations28 Oct 2015 Hachem Kadri, Emmanuel Duflos, Philippe Preux, Stéphane Canu, Alain Rakotomamonjy, Julien Audiffren

In this paper we consider the problems of supervised classification and regression in the case where attributes and labels are functions: a data is represented by a set of functions, and the label is also a function.

Audio Signal Processing General Classification

Equivalence of Learning Algorithms

no code implementations10 Jun 2014 Julien Audiffren, Hachem Kadri

The purpose of this paper is to introduce a concept of equivalence between machine learning algorithms.

BIG-bench Machine Learning regression

Online Learning with Multiple Operator-valued Kernels

no code implementations1 Nov 2013 Julien Audiffren, Hachem Kadri

We consider the problem of learning a vector-valued function f in an online learning setting.

General Classification

M-Power Regularized Least Squares Regression

no code implementations9 Oct 2013 Julien Audiffren, Hachem Kadri

Regularization is used to find a solution that both fits the data and is sufficiently smooth, and thereby is very effective for designing and refining learning algorithms.


Stability of Multi-Task Kernel Regression Algorithms

no code implementations17 Jun 2013 Julien Audiffren, Hachem Kadri

We show that multi-task kernel regression algorithms are uniformly stable in the general case of infinite-dimensional output spaces.

Multi-Task Learning regression

Multiple Operator-valued Kernel Learning

no code implementations NeurIPS 2012 Hachem Kadri, Alain Rakotomamonjy, Philippe Preux, Francis R. Bach

We study this problem in the case of kernel ridge regression for functional responses with an lr-norm constraint on the combination coefficients.


A Generalized Kernel Approach to Structured Output Learning

no code implementations10 May 2012 Hachem Kadri, Mohammad Ghavamzadeh, Philippe Preux

Finally, we evaluate the performance of our KDE approach using both covariance and conditional covariance kernels on two structured output problems, and compare it to the state-of-the-art kernel-based structured output regression methods.


Cannot find the paper you are looking for? You can Submit a new open access paper.