IFML Seminar
IFML Seminar: 09/11/26 - Robust Statistical Estimators with Bounded Empirical Sensitivity
Abstract: We introduce a new measure of robustness for statistical estimators, which we call \emph{empirical sensitivity}. An estimator $\hat\theta$ has bounded empirical sensitivity if, with high probability over a dataset $X = (X_1, \dots...
Upcoming Events
- September1111 am - 12 pm
IFML Seminar
Event DetailsAbstract: We introduce a new measure of robustness for statistical estimators, which we call \emph{empirical sensitivity}. An estimator $\hat\theta$ has...
Past Events
- March312:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Customer statistics collected in several real-world systems have reflected that users often prefer eliciting their liking for a given...
- February1012:15 - 1 pm
IFML Seminar
Event DetailsAbstract: The activation function deployed in a deep neural network has great influence on the performance of the network at...
- February312:15 - 1 pm
IFML Seminar
Event DetailsAbstract: Graph neural networks (GNNs) are successful at learning representations from most types of network data but suffer from limitations...
- January2711 am - 12 pmEvent Details
Co-hosted by UT Good Systems, Forum for Artificial Intelligence, and IFML
- January26All dayEvent Details
The University of Texas at Austin is launching a new online master’s program in AI with the potential to bring...
- January2012 - 1 pm
IFML Seminar
Event DetailsAbstract: Sparsity has widely shown its versatility in model compression, robustness improvement, and overfitting mitigation by selectively masking out a...
