Samuel Vaiter
@samuelvaiter.com
CNRS Researcher in maths & computer science. My (current) focus is machine learning and optimization. I live & work in Nice 🇫🇷
website: https://samuelvaiter.com
website: https://samuelvaiter.com
20 years later I still love this city!
August 15, 2025 at 10:41 PM
20 years later I still love this city!
Congratulations to Dr. Sophie Jaffard @sophiejaffard.bsky.social for a brillant PhD defense! We were very lucky with Patricia to have you as a PhD student, and I am sure that you will have a brillant career ahead.
July 9, 2025 at 2:08 PM
Congratulations to Dr. Sophie Jaffard @sophiejaffard.bsky.social for a brillant PhD defense! We were very lucky with Patricia to have you as a PhD student, and I am sure that you will have a brillant career ahead.
I am sure that the number of faculty follows the same curve /s
June 17, 2025 at 6:07 PM
I am sure that the number of faculty follows the same curve /s
Do you know the power of CHANI? arxiv.org/abs/2405.18828
June 11, 2025 at 3:02 PM
Do you know the power of CHANI? arxiv.org/abs/2405.18828
Even more striking, DGSWP leads to a sliced-OT based Conditional Flow Matching method with state-of-the-art results. On CIFAR-10, we show practical improvements in terms of FID wrt to I-CFM, OT-CFM and we show the practical effect of the increased expressivity of the NN-based DGSWP. 5/5
June 2, 2025 at 2:40 PM
Even more striking, DGSWP leads to a sliced-OT based Conditional Flow Matching method with state-of-the-art results. On CIFAR-10, we show practical improvements in terms of FID wrt to I-CFM, OT-CFM and we show the practical effect of the increased expressivity of the NN-based DGSWP. 5/5
The method is competitive on gradient flow tasks using either linear projection as in minSWGG, but also neural networks. We can use DGSWP either on Euclidean spaces or hyperbolic ones. 4/5
June 2, 2025 at 2:40 PM
The method is competitive on gradient flow tasks using either linear projection as in minSWGG, but also neural networks. We can use DGSWP either on Euclidean spaces or hyperbolic ones. 4/5
We show that thanks to Stein's lemma, it admits a nice differentiable approximation DGSWP, our estimator of interest. In particular, it is consistent with the original estimator, and and it yields a distance on the space of measures. 3/5
June 2, 2025 at 2:40 PM
We show that thanks to Stein's lemma, it admits a nice differentiable approximation DGSWP, our estimator of interest. In particular, it is consistent with the original estimator, and and it yields a distance on the space of measures. 3/5
A slicing scheme (min-SWGG) lifts a single 1D plan back to the original multidimensional space, selecting the slice that yields the lowest Wasserstein distance as an approximation of the full OT plan. Here, we reformulate min-SWGG as a bilevel optimization 2/5
June 2, 2025 at 2:40 PM
A slicing scheme (min-SWGG) lifts a single 1D plan back to the original multidimensional space, selecting the slice that yields the lowest Wasserstein distance as an approximation of the full OT plan. Here, we reformulate min-SWGG as a bilevel optimization 2/5
📣 New preprint 📣
**Differentiable Generalized Sliced Wasserstein Plans**
w/
L. Chapel
@rtavenar.bsky.social
We propose a Generalized Sliced Wasserstein method that provides an approximated transport plan and which admits a differentiable approximation.
arxiv.org/abs/2505.22049 1/5
**Differentiable Generalized Sliced Wasserstein Plans**
w/
L. Chapel
@rtavenar.bsky.social
We propose a Generalized Sliced Wasserstein method that provides an approximated transport plan and which admits a differentiable approximation.
arxiv.org/abs/2505.22049 1/5
June 2, 2025 at 2:40 PM
📣 New preprint 📣
**Differentiable Generalized Sliced Wasserstein Plans**
w/
L. Chapel
@rtavenar.bsky.social
We propose a Generalized Sliced Wasserstein method that provides an approximated transport plan and which admits a differentiable approximation.
arxiv.org/abs/2505.22049 1/5
**Differentiable Generalized Sliced Wasserstein Plans**
w/
L. Chapel
@rtavenar.bsky.social
We propose a Generalized Sliced Wasserstein method that provides an approximated transport plan and which admits a differentiable approximation.
arxiv.org/abs/2505.22049 1/5
Convolution theorem: Fourier transform of the convolution of two functions (under suitable assumptions) is the product of the Fourier transforms of these two functions. buff.ly/aOamDMF
May 7, 2025 at 5:01 AM
Convolution theorem: Fourier transform of the convolution of two functions (under suitable assumptions) is the product of the Fourier transforms of these two functions. buff.ly/aOamDMF
Dual numbers correspond to the completion of the real line with an nilpotent element ε different from 0. It can be thought as a universal linearization of functions, or as the forward-mode of automatic differentiation. buff.ly/vahZ0Fk
May 6, 2025 at 5:01 AM
Dual numbers correspond to the completion of the real line with an nilpotent element ε different from 0. It can be thought as a universal linearization of functions, or as the forward-mode of automatic differentiation. buff.ly/vahZ0Fk
Convergence of iterates does not imply convergence of the derivatives. Nevertheless, Gilbert (1994) proposed an interversion limit-derivative theorem under strong assumption on the spectrum of the derivatives. buff.ly/MhK7qiI
May 5, 2025 at 5:00 AM
Convergence of iterates does not imply convergence of the derivatives. Nevertheless, Gilbert (1994) proposed an interversion limit-derivative theorem under strong assumption on the spectrum of the derivatives. buff.ly/MhK7qiI
Leader-follower games, also known as Stackelberg games, are models in game theory where one player (the leader) makes a decision first, and the other player (the follower) responds, considering the leader’s action. This is one the first instance of bilevel optimization.
May 2, 2025 at 5:03 AM
Leader-follower games, also known as Stackelberg games, are models in game theory where one player (the leader) makes a decision first, and the other player (the follower) responds, considering the leader’s action. This is one the first instance of bilevel optimization.
The Matrix Mortality Problem asks if a given set of square matrices can multiply to the zero matrix after a finite sequence of multiplications of elements. It is is undecidable for matrices of size 3x3 or larger. buff.ly/lLmvvlo
May 1, 2025 at 5:01 AM
The Matrix Mortality Problem asks if a given set of square matrices can multiply to the zero matrix after a finite sequence of multiplications of elements. It is is undecidable for matrices of size 3x3 or larger. buff.ly/lLmvvlo
The SAT problem asks whether a logical formula, composed of variables and (AND, OR, NOT), can be satisfied by assigning True to the variables. SAT is NP-complete along with 3-SAT, with clauses of three literals, while 2-SAT, is in P! buff.ly/mMLGbw4
April 30, 2025 at 5:01 AM
The SAT problem asks whether a logical formula, composed of variables and (AND, OR, NOT), can be satisfied by assigning True to the variables. SAT is NP-complete along with 3-SAT, with clauses of three literals, while 2-SAT, is in P! buff.ly/mMLGbw4
The Krein-Milman theorem states that any compact convex subset of a locally convex topological vector space is the closed convex hull of its extreme points. In particular, the set of extreme points of a nonempty compact convex set is nonempty. buff.ly/6aYS8ox
April 29, 2025 at 5:01 AM
The Krein-Milman theorem states that any compact convex subset of a locally convex topological vector space is the closed convex hull of its extreme points. In particular, the set of extreme points of a nonempty compact convex set is nonempty. buff.ly/6aYS8ox
The Stone-Weierstrass theorem states that any continuous function on a compact Hausdorff space can be uniformly approximated by elements of a subalgebra, provided the subalgebra separates points and contains constants. buff.ly/MbZOAG0
April 28, 2025 at 5:01 AM
The Stone-Weierstrass theorem states that any continuous function on a compact Hausdorff space can be uniformly approximated by elements of a subalgebra, provided the subalgebra separates points and contains constants. buff.ly/MbZOAG0
The Nesterov Accelerated Gradient (NAG) algorithm refines gradient descent by using an extrapolation step before computing the gradient. It leads to faster convergence for smooth convex functions, achieving the optimal rate of O(1/k^2). www.mathnet.ru/links/ceedfb...
April 25, 2025 at 5:01 AM
The Nesterov Accelerated Gradient (NAG) algorithm refines gradient descent by using an extrapolation step before computing the gradient. It leads to faster convergence for smooth convex functions, achieving the optimal rate of O(1/k^2). www.mathnet.ru/links/ceedfb...
The pinhole camera model illustrates the concept of projective projection. Light rays from a 3D scene pass through an (infinitely) small aperture — the pinhole — and project onto a 2D surface, creating an inverted image on the focal plan. monoskop.org/images/f/ff/...
April 24, 2025 at 5:01 AM
The pinhole camera model illustrates the concept of projective projection. Light rays from a 3D scene pass through an (infinitely) small aperture — the pinhole — and project onto a 2D surface, creating an inverted image on the focal plan. monoskop.org/images/f/ff/...
Łojasiewicz inequality provides a way to control how close points are to the zeros of a real analytic function based on the value of the function itself. Extension of this result to semialgebraic or o-minimal functions exist. matwbn.icm.edu.pl/ksiazki/sm/s...
April 23, 2025 at 5:00 AM
Łojasiewicz inequality provides a way to control how close points are to the zeros of a real analytic function based on the value of the function itself. Extension of this result to semialgebraic or o-minimal functions exist. matwbn.icm.edu.pl/ksiazki/sm/s...
The fast inverse square root trick from Quake III is an algorithm to quickly approximate 1/√x, crucial for 3D graphics (normalisation). It uses bit-level manipulation and Newton's method for refinement. web.archive.org/web/20170729...
April 22, 2025 at 5:01 AM
The fast inverse square root trick from Quake III is an algorithm to quickly approximate 1/√x, crucial for 3D graphics (normalisation). It uses bit-level manipulation and Newton's method for refinement. web.archive.org/web/20170729...