Monday, 2 December 2024 @ 14:00–15:00 CET

On-site:

University of Vienna
Seminarraum 19 (OG02)
Kolingasse 14–16
1090 Vienna

Online:

https://univienna.zoom.us/j/67032386717?pwd=g8HOG2oRrWK6T5cvmRA7bv17QRzq72.1 

Meeting ID: 670 3238 6717
Passcode: 440328

Implicit bias in optimization algorithms

Abstract
:

In this talk, we will explore the role of implicit bias in optimization algorithms. Implicit bias refers to the tendency of an algorithm to converge to a specific solution even in the absence of an explicit regularization term in its formulation. In other words, implicit bias emerges from how the algorithm itself interacts with the objective function it's trying to minimize.  We will demonstrate this concept through a few surprising applications.

Bio
:

Yurii Malitskyi is an assistant professor of computational optimization at the University of Vienna. He completed his PhD at Kyiv National University in Ukraine in 2015. Following that, he held several postdoctoral positions in various European locations and served as an assistant professor in Linköping, Sweden. Yurii Malitskyi's primary research focus is continuous optimization, with applications in the field of machine learning. In 2024 he won a FWF START Award Prize. You can find more about his work at ymalitsky.com