Skip to content

Commit

Permalink
[FIX] pdfs to pngs
Browse files Browse the repository at this point in the history
  • Loading branch information
@jdumouchelle
jdumouchelle committed Apr 19, 2024
1 parent 13ca709 commit acdd619
Show file tree
Hide file tree
Showing 5 changed files with 22 additions and 17 deletions.
39 changes: 22 additions & 17 deletions index.html
View file
Original file line number Diff line number Diff line change
Expand Up @@ -119,7 +119,7 @@
<html>
<head>
<title>Neur2RO: Neural Two-Stage Robust Optimization</title>
<meta property="og:image" content="Path to my teaser.pdf"/> <!-- Facebook automatically scrapes this. Go to https://developers.facebook.com/tools/debug/ if you update and want to force Facebook to rescrape. -->
<meta property="og:image" content="Path to my teaser.png"/> <!-- Facebook automatically scrapes this. Go to https://developers.facebook.com/tools/debug/ if you update and want to force Facebook to rescrape. -->
<meta property="og:title" content="Neur2RO: Neural Two-Stage Robust Optimization" />
<meta property="og:description" content="A neural network-based technique" />

Expand All @@ -142,24 +142,24 @@
<table align=center width=1000px>
<table align=center width=900px>
<tr>
<td align=center width=200px>
<td align=center width=240px>
<center>
<span style="font-size:24px"><a href="https://jdumouchelle.github.io/">Justin Dumouchelle<sup>1</sup></a></span>
<span style="font-size:24px"><a href="https://jdumouchelle.github.io/">Justin Dumouchelle</a><sup>1</sup></span>
</center>
</td>
<td align=center width=200px>
<center>
<span style="font-size:24px"><a href="https://www.tudelft.nl/ewi/over-de-faculteit/afdelingen/applied-mathematics/people/eat-esther-julien-msc">Esther Julien<sup>2</sup></a></span>
<span style="font-size:24px"><a href="https://www.tudelft.nl/ewi/over-de-faculteit/afdelingen/applied-mathematics/people/eat-esther-julien-msc">Esther Julien</a><sup>2</sup></span>
</center>
</td>
<td align=center width=200px>
<center>
<span style="font-size:24px"><a href="https://www.uva.nl/en/profile/k/u/j.kurtz/j.kurtz.html?cb">Jannis Kurtz<sup>3</sup></a></span>
<span style="font-size:24px"><a href="https://www.uva.nl/en/profile/k/u/j.kurtz/j.kurtz.html?cb">Jannis Kurtz</a><sup>3</sup></span>
</center>
</td>
<td align=center width=200px>
<center>
<span style="font-size:24px"><a href="https://ekhalil.com/">Elias B. Khalil<sup>1</sup></a></span>
<span style="font-size:24px"><a href="https://ekhalil.com/">Elias B. Khalil</a><sup>1</sup></span>
</center>
</td>

Expand All @@ -171,12 +171,12 @@
<tr>
<td align=center width=800px>
<center>
<span><sup>1</sup>University of Toronto</span>
<span><sup>1</sup>University of Toronto, <sup>2</sup>TU Delft, <sup>3</sup>University of Amsterdam</span>
</center>

</td>
</tr>
<tr>
<!-- <tr>
<td align=center width=800px>
<center>
<span><sup>2</sup>TU Delft</span>
Expand All @@ -191,7 +191,7 @@
</center>
</td>
</tr>
</tr> -->
<tr>
<td align=center width=800px>
<center>
Expand Down Expand Up @@ -236,27 +236,28 @@
</center>
<br><br>
<center>
<table align=center width=1200px>
<table align=center width=1100px>
<tr>
<td width=260px>
<center>
<img class="round" style="width:1000px" src="./resources/teaser.pdf"/>
<img class="round" style="width:1000px" src="./resources/teaser.png"/>
</center>
</td>
</tr>
</table>
<table align=center width=850px>
<tr>
<td>
<center>
Overview of Neur2RO, a fast learning-based approximation to column-and-constraint generation (CCG) for solving two-stage robust optimization problems. In each iteration, a <i>main problem</i> (box (a)) is solved to find a good first-stage solution x for the set of scenarios that have been identified thus far (initially, none). Then, an <i>adversarial problem</i> (box (c)) is solved to obtain a new scenario for which the solution x is not feasible anymore in main problem. If no such scenario exists, then x is optimal and CCG terminates. Otherwise, the adversarial scenario is added to the set of worst-case scenarios and we iterate to main problem. For each of the main and adversarial problems, we show two versions: classical (CCG, boxes (a) and (c)) and learning-augmented (Neur2RO, dashed boxes (b) and (d))
<center>
<td style="text-align: justify; text-align-last: left;">
Overview of Neur2RO, a fast learning-based approximation to column-and-constraint generation (CCG) for solving two-stage robust optimization problems. In each iteration, a <i>main problem</i> (box (a)) is solved to find a good first-stage solution <b>x</b> for the set of scenarios that have been identified thus far (initially, none). Then, an <i>adversarial problem</i> (box (c)) is solved to obtain a new scenario for which the solution <b>x</b> is not feasible anymore in main problem. If no such scenario exists, then <b>x</b> is optimal and CCG terminates. Otherwise, the adversarial scenario is added to the set of worst-case scenarios and we iterate to main problem. For each of the main and adversarial problems, we show two versions: classical (CCG, boxes (a) and (c)) and learning-augmented (Neur2RO, dashed boxes (b) and (d))
</td>
</tr>
</table>
</center>

<br>
<hr>


<table align=center width=850px>
<center><h1>Abstract</h1></center>
<tr>
Expand All @@ -266,6 +267,7 @@
</tr>
</table>
<br>
<hr>

<!-- <hr>
<center><h1><a href='https://github.com/khalil-research/Neur2SP/tree/gh-pages/resources/Neur2SP_Slides.pdf'>[Slides]</a></h1></center>
Expand All @@ -288,14 +290,15 @@
</tr>
</table>
-->
<!-- <hr> -->
<hr>

<table align=center width=850px>
<center><h1><a href="https://www.youtube.com/watch?v=3cl0smeaTxk">[Video]</a></h1></center>
<tr>
<td>
<p align="center">
<iframe width="500" height="350" src="https://www.youtube.com/watch?v=3cl0smeaTxk"></iframe>
<iframe width="500" height="350" src="https://www.youtube.com/embed/3cl0smeaTxk"></iframe>
</p>
</td>
</tr>
Expand Down Expand Up @@ -344,10 +347,12 @@
</table> -->
<br>
<hr>
<!-- <hr> -->
<hr>
<table align=center width=800px>
<center><h1>Paper and Supplementary Material</h1></center>
<tr>
<td><a href=""><img class="layered-paper-big" style="height:175px" src="./resources/paper.pdf"/></a></td>
<td><a href=""><img class="layered-paper-big" style="height:175px" src="./resources/paper.png"/></a></td>
<td><span style="font-size:14pt">Dumouchelle, Julien, Kurtz, Khalil.<br>
<b>Neur2RO: Neural Two-Stage Robust Optimization.</b><br>
In ICLR, 2024.<br>
Expand Down
Binary file removed resources/paper.pdf
View file
Binary file not shown.
Binary file added resources/paper.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file removed resources/teaser.pdf
View file
Binary file not shown.
Binary file added resources/teaser.png
View file
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.

0 comments on commit acdd619

Please sign in to comment.