Joint work with Flore Sentenac (CREST)
Although robust learning and local differential privacy are both widely studied fields of research, combining the two settings is an almost unexplored topic. We...
Nikolas Tapia (Weierstrass Institut, Berlin)
Geometric features robust to noise of curves in Euclidean space are of great interest for various applications such as machine learning and image analysis. We apply Fels-Olver’s moving frame method (for geometric features) paired with the log-signature transform (for robust features) to construct a set of integral invariants under rigid motions for curves in Rd from the iterated-integral signature.
You are welcome to invite your friends and colleagues to join us! If you wish to attend the talks, please contact Sylvie Paycha email@example.com for the login details.