<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<b><i>"Generalized Aliasing Decomposition completely explains non-monotonic risk curves in regression"</i></b></div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
<b>Jared Whitehead</b></div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Mathematics, Numerical Analysis and Applied Mathematics Research</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Brigham Young University (BYU) </div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Please feel free to forward/share this invitation with other groups/disciplines that might be interested in this talk/topic.
<b>All are welcome to attend.</b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<i>NOTE: In-person attendance is requested in our 499 Dirac Science Library (DSL) Seminar Room. Zoom access is intended for external (non-departmental) participants only.</i></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<b>https://fsu.zoom.us/j/94273595552</b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Meeting # <b>942 7359 5552</b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<b>Wednesday, Oct 28, 2026, Schedule:</b></div>
<ul>
<li style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<div role="presentation">3:00 to 3:30 PM Eastern Time (US and Canada)</div>
</li><ul data-editing-info="{"applyListStyleFromLevel":true}" style="list-style-type: circle;">
<li style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<div role="presentation">☕ Nespresso & Teatime - 417 DSL Commons</div>
<div role="presentation"><br>
</div>
</li></ul>
<li style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<div role="presentation"><b>3:30 to 4:30 PM Eastern Time (US and Canada)</b></div>
</li><ul data-editing-info="{"applyListStyleFromLevel":true}" style="list-style-type: circle;">
<li style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<div role="presentation"><b>🕟 Colloquium - 499 DSL Seminar Room</b></div>
</li></ul>
</ul>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<b>Abstract:</b></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
A central problem in data science is to use potentially noisy samples of an unknown function to predict function values for unseen inputs. In classical statistics, the predictive error is understood as a trade-off between the bias and the variance that balances
model simplicity with its ability to fit complex functions. However, overparametrized models exhibit counterintuitive behaviors, such as “double descent” in which models of increasing complexity exhibit decreasing generalization error. Other models may exhibit
more complicated patterns of predictive error with multiple peaks and valleys. Neither double descent nor multiple descent phenomena are well explained by the bias-variance decomposition. We introduce a decomposition that we call the generalized aliasing decomposition
(GAD) to explain the relationship between predictive performance and model complexity. The GAD decomposes the predictive error into three parts: (1) model insufficiency, which dominates when the number of parameters is much smaller than the number of data
points, (2) data insufficiency, which dominates when the number of parameters is much greater than the number of data points, and (3) generalized aliasing, which dominates between these two extremes. We demonstrate the applicability of the GAD to diverse applications,
including random feature models from machine learning, Fourier transforms from signal processing, solution methods for differential equations, and predictive formation enthalpy in materials discovery. Because key components of the generalized aliasing decomposition
can be explicitly calculated from the relationship between model class and samples without seeing any data labels, it can answer questions related to experimental design and model selection before collecting data or performing experiments. We further demonstrate
this approach on several examples and discuss implications for predictive modeling and data science.</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div class="elementToProof" style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Additional colloquium details can be found here:</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<a href="https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.sc.fsu.edu%2Fnews-and-events%2Fcolloquium%2Fcolloquium-with-jared-whitehead-2026-10-28&data=05%7C02%7Csc-seminar-announce%40lists.fsu.edu%7Cbd25305ef74841b4092e08df32ad2b61%7Ca36450ebdb0642a78d1b026719f701e3%7C0%7C0%7C639285391459108259%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=AL7Gd0tZNlNXgoJNp8UTJSpMod8p%2BiX3lEDLwy%2FIsNo%3D&reserved=0" originalsrc="https://www.sc.fsu.edu/news-and-events/colloquium/colloquium-with-jared-whitehead-2026-10-28">https://www.sc.fsu.edu/news-and-events/colloquium/colloquium-with-jared-whitehead-2026-10-28</a></div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
🎦 Colloquium recordings will be made available here:</div>
<div style="font-family: Tahoma, Geneva, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<a href="https://nam04.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.sc.fsu.edu%2Fnews-and-events%2Fseminars&data=05%7C02%7Csc-seminar-announce%40lists.fsu.edu%7Cbd25305ef74841b4092e08df32ad2b61%7Ca36450ebdb0642a78d1b026719f701e3%7C0%7C0%7C639285391459122159%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=ypQvTUCAxnEOVoiwgAz4LK9z%2F%2BtG%2Bh5ju6DICXsgM54%3D&reserved=0" originalsrc="https://www.sc.fsu.edu/news-and-events/seminars" id="OWAbb68cc6f-e015-cdcc-966f-7beed24fb1b3" class="OWAAutoLink">https://www.sc.fsu.edu/news-and-events/seminars</a></div>
</body>
</html>