Events
This week
×
Modal title
Modal content
Monday, 26 June | |||
---|---|---|---|
— no events scheduled — |
Tuesday, 27 June | |||
---|---|---|---|
Time | Speaker | Title | Location |
14:15 - 16:00 |
Prof. Dr. Nikita Zhivotovskiycall_made University of California Berkeley, Department of Statistics |
Abstract
In statistical learning theory, determining the sample complexity of realizable binary classification for VC classes was a long-standing open problem. The results of Simon and Hanneke established sharp upper bounds in this setting. However, the reliance of their argument on the uniform convergence principle limits its applicability to more general learning settings such as multiclass classification. In this talk, we will discuss a simple technique that addresses this issue. We will present optimal high probability risk bounds through a framework that surpasses the limitations of uniform convergence arguments.
In addition to binary classification, we will see applications in settings where uniform convergence is provably sub-optimal. For multiclass classification, we prove an optimal risk bound scaling with the one-inclusion hypergraph density of the class, addressing the suboptimality of the analysis by Daniely and Shalev-Shwartz.
Based on joint work with Ishaq Aden-Ali, Yeshwanth Cherapanamjeri and Abhishek Shetty.
DACO SeminarOptimal PAC Bounds without Uniform Convergence.read_more |
HG G 19.2 |
Wednesday, 28 June | |||
---|---|---|---|
— no events scheduled — |
Thursday, 29 June | |||
---|---|---|---|
Time | Speaker | Title | Location |
09:30 - 11:00 |
Hanna Wutte Examiner: Prof. Dr. Josef Teichmann |
Abstract
A Take on Deep Learning in Finance: Uncertainty Quantification and Dynamic Decision Making |
HG D 16.2 |
Friday, 30 June | |||
---|---|---|---|
Time | Speaker | Title | Location |
09:15 - 10:45 |
Marco Petrella Examiner: Prof. Dr. Sid Mishra |
HG G 19.1 |