Active Nearest Neighbor Regression Through Delaunay Refinement

no code implementations • 16 Jun 2022 • Alexander Kravberg, Giovanni Luca Marchetti, Vladislav Polianskii, Anastasiia Varava, Florian T. Pokorny, Danica Kragic

We introduce an algorithm for active function approximation based on nearest neighbor regression.

regression

Delaunay Component Analysis for Evaluation of Data Representations

1 code implementation • ICLR 2022 • Petra Poklukar, Vladislav Polianskii, Anastasia Varava, Florian Pokorny, Danica Kragic

Advanced representation learning techniques require reliable and general evaluation methods.

Representation Learning

Witness Autoencoder: Shaping the Latent Space with Witness Complexes

no code implementations • NeurIPS Workshop TDA_and_Beyond 2020 • Simon Till Schönenberger, Anastasiia Varava, Vladislav Polianskii, Jen Jen Chung, Danica Kragic, Roland Siegwart

We present a Witness Autoencoder (W-AE) – an autoencoder that captures geodesic distances of the data in the latent space.