add slides and videos

Author: sebcolla

february_2023/assets/slides/ADMM_slides.pdf

@@ -238,6 +238,7 @@ <h2>Monday the 13th</h2>
                     of the given bounds. Moreover, we study the linear (R-linear) convergence of ADMM under some
                     scenarios which are weaker than the existing ones in the literature.
                 </details>
+                [<a href="https://arxiv.org/pdf/2206.09865.pdf" target="_blank"> Preprint </a>, <a href="assets\slides\ADMM_slides.pdf"  target="_blank"> Slides </a>, <a href="https://youtu.be/kddBAuaqJ4g"  target="_blank"> Video </a> ]
             </td>
 
         </tr>
@@ -363,9 +364,9 @@ <h2>Tuesday the 14th</h2>
                     differential equations. More precisely, we extend the performance estimation framework, originally
                     proposed by Drori and Teboulle (2012), to continuous-time models. We retrieve convergence results
                     comparable to those of discrete methods using fewer assumptions and convexity inequalities, and provide
-                    new results for stochastic accelerated gradient flows. <br>
+                    new results for stochastic accelerated gradient flows.
                 </details>
-                <br>
+                [<a href="https://arxiv.org/pdf/2205.12772.pdf" target="_blank"> Preprint </a>, <a href="assets\slides\PEP-talks2023 - Celine Moucer.pdf"  target="_blank"> Slides </a>, <a href="https://youtu.be/nrtErdTf7m0" target="_blank"> Video </a>] <br> <br>
                 <details>
                 <summary><i>Yassine Kamri (UCLouvain)</i> - <strong>On the worst-case analysis of block coordinate-wise algorithms  </strong> </summary>
                 Block coordinate-wise algorithms are an essential class of first-order optimization methods widely used