Implicit bias in optimization algorithms

by Dr Yurii Malitskyi (University of Vienna, Austria)

Wednesday 20 May 2026, 17:00 → 18:00 Europe/Kiev

https://knu-ua.zoom.us/j/89643295643?pwd=eTBZZSt0d0thZzFyaUhDUFNGTVE3QT09 (ONLINE)

 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.