Skip to content

Commit ca2df6c

Browse files
klamikeklamike
authored
comment l2o org
1 parent c88010d commit ca2df6c

File tree

1 file changed

+137
-137
lines changed

1 file changed

+137
-137
lines changed

‎class01/class01_intro.jl‎

Lines changed: 137 additions & 137 deletions
Original file line numberDiff line numberDiff line change
@@ -210,143 +210,143 @@ md"[^OptProx]"
210210
211211
"""
212212

213-
# ╔═╡ 45275d44-e268-43cb-8156-feecd916a6da
214-
@htl """
215-
<div style="
216-
border:1px solid #ccc;
217-
border-radius:6px;
218-
padding:1rem;
219-
font-size:0.9rem;
220-
max-width:760px;
221-
line-height:1.45;
222-
">
223-
224-
<!-- ─────────────────────── header ─────────────────────── -->
225-
<h2 style="margin-top:0">LearningToOptimize&nbsp;Organization</h2>
226-
227-
<p>
228-
<strong>LearningToOptimize&nbsp;(L2O)</strong> is a collection of open-source tools
229-
focused on the emerging paradigm of <em>amortized optimization</em>—using machine-learning
230-
methods to accelerate traditional constrained-optimization solvers.
231-
<em>L2O is a work-in-progress; existing functionality is considered experimental and may
232-
change.</em>
233-
</p>
234-
235-
<!-- ─────────────────── repositories table ──────────────── -->
236-
<h3>Open-Source&nbsp;Repositories</h3>
237-
238-
<table style="border-collapse:collapse;width:100%">
239-
<tbody>
240-
<tr>
241-
<td style="padding:4px 6px;vertical-align:top;">
242-
<a href="https://github.com/LearningToOptimize/LearningToOptimize.jl"
243-
target="_blank">LearningToOptimize.jl</a>
244-
</td>
245-
<td style="padding:4px 6px;">
246-
Flagship Julia package that wraps data generation, training loops and evaluation
247-
utilities for fitting surrogate models to parametric optimization problems.
248-
</td>
249-
</tr>
250-
251-
<tr>
252-
<td style="padding:4px 6px;vertical-align:top;">
253-
<a href="https://github.com/andrewrosemberg/DecisionRules.jl"
254-
target="_blank">DecisionRules.jl</a>
255-
</td>
256-
<td style="padding:4px 6px;">
257-
Build decision rules for multistage stochastic programs, as proposed in
258-
<a href="https://arxiv.org/pdf/2405.14973" target="_blank"><em>Efficiently
259-
Training Deep-Learning Parametric Policies using Lagrangian Duality</em></a>.
260-
</td>
261-
</tr>
262-
263-
<tr>
264-
<td style="padding:4px 6px;vertical-align:top;">
265-
<a href="https://github.com/LearningToOptimize/L2OALM.jl"
266-
target="_blank">L2OALM.jl</a>
267-
</td>
268-
<td style="padding:4px 6px;">
269-
Implementation of the primal-dual learning method <strong>ALM</strong>,
270-
introduced in
271-
<a href="https://ojs.aaai.org/index.php/AAAI/article/view/25520" target="_blank">
272-
<em>Self-Supervised Primal-Dual Learning for Constrained Optimization</em></a>.
273-
</td>
274-
</tr>
275-
276-
<tr>
277-
<td style="padding:4px 6px;vertical-align:top;">
278-
<a href="https://github.com/LearningToOptimize/L2ODLL.jl"
279-
target="_blank">L2ODLL.jl</a>
280-
</td>
281-
<td style="padding:4px 6px;">
282-
Implementation of the dual learning method <strong>DLL</strong>,
283-
proposed in
284-
<a href="https://neurips.cc/virtual/2024/poster/94146" target="_blank">
285-
<em>Dual Lagrangian Learning for Conic Optimization</em></a>.
286-
</td>
287-
</tr>
288-
289-
<tr>
290-
<td style="padding:4px 6px;vertical-align:top;">
291-
<a href="https://github.com/LearningToOptimize/L2ODC3.jl"
292-
target="_blank">L2ODC3.jl</a>
293-
</td>
294-
<td style="padding:4px 6px;">
295-
Implementation of the primal learning method <strong>DC3</strong>, as described in
296-
<a href="https://openreview.net/forum?id=V1ZHVxJ6dSS" target="_blank">
297-
<em>DC3: A Learning Method for Optimization with Hard Constraints</em></a>.
298-
</td>
299-
</tr>
300-
301-
<tr>
302-
<td style="padding:4px 6px;vertical-align:top;">
303-
<a href="https://github.com/LearningToOptimize/BatchNLPKernels.jl"
304-
target="_blank">BatchNLPKernels.jl</a>
305-
</td>
306-
<td style="padding:4px 6px;">
307-
GPU kernels that evaluate objectives, Jacobians and Hessians for
308-
<strong>batches</strong> of
309-
<a href="https://github.com/exanauts/ExaModels.jl" target="_blank">ExaModels</a>,
310-
useful when defining loss functions for large-batch ML predictions.
311-
</td>
312-
</tr>
313-
314-
<tr>
315-
<td style="padding:4px 6px;vertical-align:top;">
316-
<a href="https://github.com/LearningToOptimize/BatchConeKernels.jl"
317-
target="_blank">BatchConeKernels.jl</a>
318-
</td>
319-
<td style="padding:4px 6px;">
320-
GPU kernels for batched cone operations (projections, distances, etc.),
321-
enabling advanced architectures such as repair layers.
322-
</td>
323-
</tr>
324-
325-
<tr>
326-
<td style="padding:4px 6px;vertical-align:top;">
327-
<a href="https://github.com/LearningToOptimize/LearningToControlClass"
328-
target="_blank">LearningToControlClass</a>
329-
</td>
330-
<td style="padding:4px 6px;">
331-
Course repository for <em>Special Topics on Optimal Control &amp; Learning</em>
332-
(Fall 2025, Georgia Tech).
333-
</td>
334-
</tr>
335-
</tbody>
336-
</table>
337-
338-
<!-- ─────────────── datasets and weights ──────────────── -->
339-
<h3 style="margin-top:1.25rem;">Open Datasets and Weights</h3>
340-
341-
<p>
342-
The
343-
<a href="https://huggingface.co/LearningToOptimize" target="_blank">
344-
LearningToOptimize&nbsp;🤗 Hugging Face organization</a>
345-
hosts datasets and pre-trained weights that can be used with L2O packages.
346-
</p>
347-
348-
</div>
349-
"""
213+
# # ╔═╡ 45275d44-e268-43cb-8156-feecd916a6da
214+
# @htl """
215+
# <div style="
216+
# border:1px solid #ccc;
217+
# border-radius:6px;
218+
# padding:1rem;
219+
# font-size:0.9rem;
220+
# max-width:760px;
221+
# line-height:1.45;
222+
# ">
223+
224+
# <!-- ─────────────────────── header ─────────────────────── -->
225+
# <h2 style="margin-top:0">LearningToOptimize&nbsp;Organization</h2>
226+
227+
# <p>
228+
# <strong>LearningToOptimize&nbsp;(L2O)</strong> is a collection of open-source tools
229+
# focused on the emerging paradigm of <em>amortized optimization</em>—using machine-learning
230+
# methods to accelerate traditional constrained-optimization solvers.
231+
# <em>L2O is a work-in-progress; existing functionality is considered experimental and may
232+
# change.</em>
233+
# </p>
234+
235+
# <!-- ─────────────────── repositories table ──────────────── -->
236+
# <h3>Open-Source&nbsp;Repositories</h3>
237+
238+
# <table style="border-collapse:collapse;width:100%">
239+
# <tbody>
240+
# <tr>
241+
# <td style="padding:4px 6px;vertical-align:top;">
242+
# <a href="https://github.com/LearningToOptimize/LearningToOptimize.jl"
243+
# target="_blank">LearningToOptimize.jl</a>
244+
# </td>
245+
# <td style="padding:4px 6px;">
246+
# Flagship Julia package that wraps data generation, training loops and evaluation
247+
# utilities for fitting surrogate models to parametric optimization problems.
248+
# </td>
249+
# </tr>
250+
251+
# <tr>
252+
# <td style="padding:4px 6px;vertical-align:top;">
253+
# <a href="https://github.com/andrewrosemberg/DecisionRules.jl"
254+
# target="_blank">DecisionRules.jl</a>
255+
# </td>
256+
# <td style="padding:4px 6px;">
257+
# Build decision rules for multistage stochastic programs, as proposed in
258+
# <a href="https://arxiv.org/pdf/2405.14973" target="_blank"><em>Efficiently
259+
# Training Deep-Learning Parametric Policies using Lagrangian Duality</em></a>.
260+
# </td>
261+
# </tr>
262+
263+
# <tr>
264+
# <td style="padding:4px 6px;vertical-align:top;">
265+
# <a href="https://github.com/LearningToOptimize/L2OALM.jl"
266+
# target="_blank">L2OALM.jl</a>
267+
# </td>
268+
# <td style="padding:4px 6px;">
269+
# Implementation of the primal-dual learning method <strong>ALM</strong>,
270+
# introduced in
271+
# <a href="https://ojs.aaai.org/index.php/AAAI/article/view/25520" target="_blank">
272+
# <em>Self-Supervised Primal-Dual Learning for Constrained Optimization</em></a>.
273+
# </td>
274+
# </tr>
275+
276+
# <tr>
277+
# <td style="padding:4px 6px;vertical-align:top;">
278+
# <a href="https://github.com/LearningToOptimize/L2ODLL.jl"
279+
# target="_blank">L2ODLL.jl</a>
280+
# </td>
281+
# <td style="padding:4px 6px;">
282+
# Implementation of the dual learning method <strong>DLL</strong>,
283+
# proposed in
284+
# <a href="https://neurips.cc/virtual/2024/poster/94146" target="_blank">
285+
# <em>Dual Lagrangian Learning for Conic Optimization</em></a>.
286+
# </td>
287+
# </tr>
288+
289+
# <tr>
290+
# <td style="padding:4px 6px;vertical-align:top;">
291+
# <a href="https://github.com/LearningToOptimize/L2ODC3.jl"
292+
# target="_blank">L2ODC3.jl</a>
293+
# </td>
294+
# <td style="padding:4px 6px;">
295+
# Implementation of the primal learning method <strong>DC3</strong>, as described in
296+
# <a href="https://openreview.net/forum?id=V1ZHVxJ6dSS" target="_blank">
297+
# <em>DC3: A Learning Method for Optimization with Hard Constraints</em></a>.
298+
# </td>
299+
# </tr>
300+
301+
# <tr>
302+
# <td style="padding:4px 6px;vertical-align:top;">
303+
# <a href="https://github.com/LearningToOptimize/BatchNLPKernels.jl"
304+
# target="_blank">BatchNLPKernels.jl</a>
305+
# </td>
306+
# <td style="padding:4px 6px;">
307+
# GPU kernels that evaluate objectives, Jacobians and Hessians for
308+
# <strong>batches</strong> of
309+
# <a href="https://github.com/exanauts/ExaModels.jl" target="_blank">ExaModels</a>,
310+
# useful when defining loss functions for large-batch ML predictions.
311+
# </td>
312+
# </tr>
313+
314+
# <tr>
315+
# <td style="padding:4px 6px;vertical-align:top;">
316+
# <a href="https://github.com/LearningToOptimize/BatchConeKernels.jl"
317+
# target="_blank">BatchConeKernels.jl</a>
318+
# </td>
319+
# <td style="padding:4px 6px;">
320+
# GPU kernels for batched cone operations (projections, distances, etc.),
321+
# enabling advanced architectures such as repair layers.
322+
# </td>
323+
# </tr>
324+
325+
# <tr>
326+
# <td style="padding:4px 6px;vertical-align:top;">
327+
# <a href="https://github.com/LearningToOptimize/LearningToControlClass"
328+
# target="_blank">LearningToControlClass</a>
329+
# </td>
330+
# <td style="padding:4px 6px;">
331+
# Course repository for <em>Special Topics on Optimal Control &amp; Learning</em>
332+
# (Fall 2025, Georgia Tech).
333+
# </td>
334+
# </tr>
335+
# </tbody>
336+
# </table>
337+
338+
# <!-- ─────────────── datasets and weights ──────────────── -->
339+
# <h3 style="margin-top:1.25rem;">Open Datasets and Weights</h3>
340+
341+
# <p>
342+
# The
343+
# <a href="https://huggingface.co/LearningToOptimize" target="_blank">
344+
# LearningToOptimize&nbsp;🤗 Hugging Face organization</a>
345+
# hosts datasets and pre-trained weights that can be used with L2O packages.
346+
# </p>
347+
348+
# </div>
349+
# """
350350

351351
# ╔═╡ c08f511e-b91d-4d17-a286-96469c31568a
352352
md"## Example: Robotic Arm Manipulation"

0 commit comments

Comments
 (0)