Speaker: Santiago Rattenbach Paliza Bartolomé.
Abstract: In this talk, an innovative approach to data imputation with TabImpute is presented, leveraging the regression capabilities of TabPFN. Specifically, the comparison between TabImpute and the previous approach to data imputation using TabPFN is addressed, highlighting their differences both in terms of implementation and performance. Finally, the possibility of improving the performance of a TabPFN regressor model through prior data imputation with TabImpute, instead of working with incomplete data, is explored.