<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p></p>
<div class="moz-forward-container">
<div id="website_title">
<div><b>DEEPK 2024<br>
<i>International Workshop on Deep Learning and Kernel
Machines</i></b><br>
</div>
<div><br>
</div>
<div>March 7-8, 2024, Leuven, Arenberg Castle, Belgium<br>
<a class="moz-txt-link-freetext"
href="https://www.esat.kuleuven.be/stadius/E/DEEPK2024"
moz-do-not-send="true">https://www.esat.kuleuven.be/stadius/E/DEEPK2024</a></div>
<div><br>
</div>
<div><b><i>- Main scope -</i></b><br>
</div>
<div><br>
</div>
<div>Major progress and impact has been achieved through deep
learning architectures with many exciting applications such as
by generative models and transformers. At the same time it
triggers new questions on the fundamental possibilities and
limitations of the models, with respect to representations,
scalability, learning and generalization aspects. Through
kernel-based methods often a deeper understanding and solid
foundations have been obtained, complementary to the powerful
and flexible deep learning architectures. Recent examples are
understanding generalization of over-parameterized models in
the double descent phenomenon and conceiving attention
mechanisms in transformers as kernel machines. The aim of
DEEPK 2024 is to provide a multi-disciplinary forum where
researchers of different communities can meet, to find new
synergies between deep learning and kernel machines, both at
the level of theory and applications. <br>
</div>
<div><br>
</div>
<div><b><i>- Topics - </i></b><br>
</div>
<div><br>
</div>
<div>Topics include but are not limited to:<br>
<ul>
<li>Deep learning and generalization </li>
<li>Double descent phenomenon and over-parameterized models
</li>
<li>Transformers and asymmetric kernels </li>
<li>Attention mechanisms, kernel singular value
decomposition </li>
<li>Learning with asymmetric kernels </li>
<li>Duality and deep learning </li>
<li>Regularization schemes, normalization </li>
<li>Neural tangent kernel </li>
<li>Deep learning and Gaussian processes </li>
<li>Transformers, support vector machines and least squares
support vector machines </li>
<li>Autoencoders, neural networks and kernel methods </li>
<li>Kernel methods in GANs, variational autoencoders,
diffusion models, Generative Flow Networks </li>
<li>Generative kernel machines </li>
<li>Deep Kernel PCA, deep kernel machines, deep eigenvalues,
deep eigenvectors </li>
<li>Restricted Boltzmann machines, Restricted kernel
machines, deep learning, energy based models </li>
<li>Disentanglement and explainability </li>
<li>Tensors, kernels and deep learning </li>
<li>Convolutional kernels </li>
<li>Sparsity, robustness, low-rank representations,
compression </li>
<li>Nystrom method, Nystromformer </li>
<li>Efficient training methods </li>
<li>Lagrange duality, Fenchel duality, estimation in Hilbert
spaces, reproducing kernel Hilbert spaces, vector-valued
reproducing kernel Hilbert spaces, Krein spaces, Banach
spaces, RKHS and C*-algebra</li>
<li>Applications</li>
</ul>
<br>
</div>
<div><b><i>- Invited Speakers -</i></b><br>
</div>
<div>
<ul>
<li><a href="http://misha.belkin-wang.org/"
moz-do-not-send="true">Mikhail Belkin</a> (University of
California San Diego)<br>
</li>
<li><a href="https://www.epfl.ch/labs/lions/"
moz-do-not-send="true">Volkan Cevher</a> (EPFL)<br>
</li>
<li><a href="https://perso.telecom-paristech.fr/fdalche/"
moz-do-not-send="true">Florence d'Alche-Buc</a><a
moz-do-not-send="true"> (Telecom Paris, Institut
Polytechnique de Paris)<br>
</a></li>
<li><a href="https://lear.inrialpes.fr/people/mairal/"
moz-do-not-send="true">Julien Mairal</a> (INRIA)<br>
</li>
<li><a href="https://www.iit.it/people/massimiliano-pontil"
moz-do-not-send="true">Massimiliano Pontil</a> (IIT and
University College London)<br>
</li>
<li><a
href="https://www.maths.usyd.edu.au/ut/people?who=DX_Zhou&sms=y"
moz-do-not-send="true">Dingxuan Zhou</a> (University of
Sydney)<br>
</li>
</ul>
</div>
<div><br>
</div>
<div><b><i>- Call for abstracts -</i></b></div>
<div><br>
</div>
<div>The DEEPK 2024 program will include <b>oral and poster
sessions</b>. Interested participants are cordially invited
to submit an <b>extended abstract (max. 2 pages)</b> for
their contribution. Please prepare your extended abstract
submission in LaTeX, according to the provided stylefile and
submit it in pdf format (max. 2 pages). Further extended
abstract information will be given at <a
class="moz-txt-link-freetext"
href="https://www.esat.kuleuven.be/stadius/E/DEEPK2024/call_for_abstracts.php"
moz-do-not-send="true">https://www.esat.kuleuven.be/stadius/E/DEEPK2024/call_for_abstracts.php</a>
.</div>
<div><br>
</div>
<div><b><i>- Schedule - </i></b><br>
</div>
<div>
<ul>
<li><b>Deadline extended abstract submission:</b><br>
Feb 8, 2024 </li>
<li>Notification of acceptance and presentation format
(oral/poster):<br>
Feb 22, 2024 </li>
<li>Deadline for registration:<br>
Feb 29, 2024 <br>
</li>
<li><b>International Workshop DEEPK 2024:</b><br>
<span style="color:#990000;font-weight:bold"> March 7-8,
2024</span> </li>
</ul>
</div>
<div><b><i>- Organizing committee - </i></b><br>
</div>
<div><br>
</div>
<div>Johan Suykens (Chair), Alex Lambert, Panos Patrinos,
Qinghua Tao, Francesco Tonin</div>
<div><br>
</div>
<div><b><i>- Other info -</i></b></div>
<div><br>
</div>
<div>Please consult the DEEPK 2024 website <a
class="moz-txt-link-freetext"
href="https://www.esat.kuleuven.be/stadius/E/DEEPK2024"
moz-do-not-send="true">https://www.esat.kuleuven.be/stadius/E/DEEPK2024</a>
for info on program, registration, location and venue. The
event is co-sponsored by ERC Advanced Grant E-DUALITY and KU
Leuven.<br>
</div>
<div><br>
</div>
<div><br>
</div>
<div><br>
</div>
<div><br>
</div>
<div><br>
</div>
</div>
</div>
</body>
</html>