$$ \newcommand{\DD}{\mathbb{D}} \newcommand{\NN}{\mathbb{N}} \newcommand{\CC}{\mathbb{C}} \newcommand{\GG}{\mathbb{G}} \newcommand{\LL}{\mathbb{L}} \newcommand{\PP}{\mathbb{P}} \newcommand{\QQ}{\mathbb{Q}} \newcommand{\RR}{\mathbb{R}} \newcommand{\VV}{\mathbb{V}} \newcommand{\ZZ}{\mathbb{Z}} \newcommand{\FF}{\mathbb{F}} \newcommand{\KK}{\mathbb{K}} \newcommand{\UU}{\mathbb{U}} \newcommand{\EE}{\mathbb{E}} \newcommand{\Aa}{\mathcal{A}} \newcommand{\Bb}{\mathcal{B}} \newcommand{\Cc}{\mathcal{C}} \newcommand{\Dd}{\mathcal{D}} \newcommand{\Ee}{\mathcal{E}} \newcommand{\Ff}{\mathcal{F}} \newcommand{\Gg}{\mathcal{G}} \newcommand{\Hh}{\mathcal{H}} \newcommand{\Ii}{\mathcal{I}} \newcommand{\Jj}{\mathcal{J}} \newcommand{\Kk}{\mathcal{K}} \newcommand{\Ll}{\mathcal{L}} \newcommand{\Mm}{\mathcal{M}} \newcommand{\Nn}{\mathcal{N}} \newcommand{\Oo}{\mathcal{O}} \newcommand{\Pp}{\mathcal{P}} \newcommand{\Qq}{\mathcal{Q}} \newcommand{\Rr}{\mathcal{R}} \newcommand{\Ss}{\mathcal{S}} \newcommand{\Tt}{\mathcal{T}} \newcommand{\Uu}{\mathcal{U}} \newcommand{\Vv}{\mathcal{V}} \newcommand{\Ww}{\mathcal{W}} \newcommand{\Xx}{\mathcal{X}} \newcommand{\Yy}{\mathcal{Y}} \newcommand{\Zz}{\mathcal{Z}} \DeclareMathOperator{\Ker}{Ker} \DeclareMathOperator{\nullspace}{null} \DeclareMathOperator{\Hom}{Hom} \DeclareMathOperator{\End}{End} \DeclareMathOperator{\tr}{tr} \DeclareMathOperator{\Tr}{Tr} \DeclareMathOperator{\Supp}{Supp} \DeclareMathOperator{\Sign}{Sign} \DeclareMathOperator{\Corr}{Corr} \DeclareMathOperator{\sign}{sign} \DeclareMathOperator{\supp}{supp} \DeclareMathOperator{\epigraph}{epi} \DeclareMathOperator{\graph}{graph} \DeclareMathOperator{\dom}{dom} \DeclareMathOperator{\cas}{cas} \DeclareMathOperator{\sinc}{sinc} \DeclareMathOperator{\cotan}{cotan} \DeclareMathOperator{\Card}{Card} \DeclareMathOperator{\PGCD}{PGCD} \DeclareMathOperator{\Span}{Span} \DeclareMathOperator{\Vect}{Vect} \DeclareMathOperator{\Grad}{grad} \DeclareMathOperator{\diag}{diag} \DeclareMathOperator{\rank}{rank} \DeclareMathOperator{\interop}{int} \DeclareMathOperator{\rint}{ri} \DeclareMathOperator{\bd}{bd} \DeclareMathOperator{\rbd}{rbd} \DeclareMathOperator{\Conv}{Conv} \newcommand{\bConv}{\overline{\Conv}} \DeclareMathOperator{\epi}{epi} \DeclareMathOperator{\co}{co} \newcommand{\bco}{\overline{\co}} \DeclareMathOperator{\Var}{Var} \DeclareMathOperator{\diverg}{div} \DeclareMathOperator{\Prox}{Prox} \newcommand{\Jaco}[1]{J_{#1}} \newcommand{\Calpha}{\mathrm{C}^\al} \newcommand{\Cbeta}{\mathrm{C}^\be} \newcommand{\Cal}{\text{C}^\al} \newcommand{\Cdeux}{\mathrm{C}^{2}} \newcommand{\Calt}[1]{\mathrm{C}^{#1}} \renewcommand{\d}{\ins{d}} \newcommand{\RRb}{\overline{\RR}} \renewcommand{\epsilon}{\varepsilon} \renewcommand{\imath}{\mathrm{i}} \newcommand{\dotp}[2]{\langle #1,\,#2\rangle} \newcommand{\norm}[1]{|\!| #1 |\!|} \newcommand{\abs}[1]{| #1 |} \newcommand{\bregman}[3]{D_{#1}(x\|y)} \newcommand{\transp}[1]{#1^{*}} \DeclareMathOperator{\Id}{Id} \DeclareMathOperator{\argmin}{argmin} \DeclareMathOperator{\argmax}{argmax} \DeclareMathOperator{\Argmin}{Argmin} \DeclareMathOperator{\Argmax}{Argmax} \newcommand{\uargmin}[1]{\underset{#1}{\argmin}\;} \newcommand{\uargmax}[1]{\underset{#1}{\argmax}\;} \newcommand{\uArgmin}[1]{\underset{#1}{\Argmin}\;} \newcommand{\uArgmax}[1]{\underset{#1}{\Argmax}\;} \newcommand{\umin}[1]{\underset{#1}{\min}\;} \newcommand{\umax}[1]{\underset{#1}{\max}\;} \newcommand{\usup}[1]{\underset{#1}{\sup}\;} \newcommand{\set}[1]{ \{ #1 \} } \newcommand{\bset}[1]{ \left\{ #1 \right\} } \newcommand{\setcond}[2]{ \left\{ #1 \;:\; #2 \right\} } $$
Samuel Vaiter
Home
Publications
Talks
Posts
Teaching
About
Posts / Notes / Blogposts
Categories
All
(4)
graphs
(1)
lecture-notes
(3)
machine-learning
(1)
optimization
(3)
What’s a Graph Neural Network?
A short introduction to Graph Neural Networks through a spectral lens.
Feb 15, 2024
Adding some noise
Introduction to the Stochastic Gradient Descent algorithm.
Feb 9, 2024
Following the steepest direction
Short introduction to the gradient descent algorithm.
Feb 8, 2024
A first look at convex analysis
Crash course in convexity to have just enough material to study the gradient descent.
Feb 7, 2024
No matching items