<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii">
</head>
<body>
<div class="BodyFragment"><font size="2"><span style="font-size:11pt;">
<div class="PlainText">This is an announcement of Owen Melia's MS Presentation<br>
===============================================<br>
Candidate: Owen Melia<br>
<br>
Date: Friday, March 03, 2023<br>
<br>
Time: 3:45 pm CST<br>
<br>
Location: JCL 223<br>
<br>
M.S. Paper Title: ROTATION-INVARIANT RANDOM FEATURES PROVIDE A STRONG BASELINE FOR MACHINE LEARNING ON 3D POINT CLOUDS<br>
<br>
Abstract: Rotational invariance is a popular inductive bias used by many fields in machine learning,<br>
such as computer vision and machine learning for quantum chemistry. Rotation-invariant<br>
machine learning methods set the state of the art for many tasks, including molecular property<br>
prediction and 3D shape classification. These methods generally either rely on taskspecific<br>
rotation-invariant features, or they use general-purpose deep neural networks which<br>
are complicated to design and train. We suggest a simple and general-purpose method for<br>
learning rotation-invariant functions of three-dimensional point cloud data using a random<br>
features approach. Specifically, we extend the random features method of Rahimi and Recht<br>
[2007] by deriving a version that is invariant to three-dimensional rotations and showing<br>
that it is fast to evaluate on point cloud data. We show through experiments that our<br>
method matches or outperforms the performance of general-purpose invariant architectures<br>
on standard molecular property prediction benchmark datasets QM7 and QM9. We also<br>
show that our method is competitive with other general-purpose invariant architectures on<br>
the ModelNet40 shape classification task. Finally, we show that our method is an order of<br>
magnitude faster at prediction time than competing kernel methods.<br>
<br>
Advisors: Rebecca Willett<br>
<br>
Committee Members: Risi Kondor, Eric Jonas, and Rebecca Willett<br>
<br>
</div>
</span></font></div>
<div class="BodyFragment"><font size="2"><span style="font-size:11pt;">
<div class="PlainText"><br>
<br>
<br>
</div>
</span></font></div>
</body>
</html>