Montag, 12. Juni 2023, 16:45 - 17:45 iCal

ISOR Colloquium

"Learning Robustly from Multiple Sources"

Speaker: Christoph Lampert (Institute of Science and Technology Austria, Austria)

HS 7 OMP1 (#1.303)
Oskar-Morgenstern-Platz 1, 1090 Wien

Vortrag

---

We study the problem of learning from multiple untrusted data sources, a scenario of increasing practical relevance given the recent emergence of crowdsourcing and collaborative learning paradigms. Specifically, we analyze the situation in which a learning system obtains datasets from multiple sources, some of which might be biased or even adversarially perturbed. It is known that in the single-source case, an adversary with the power to corrupt a fixed fraction of the training data can prevent "learnability", that is, even in the limit of infinitely much training data, no learning system can approach the optimal test error. I present recent work with Nikola Konstantinov in which we show that, surprisingly, the same is not true in the multi-source setting, where the adversary can arbitrarily corrupt a fixed fraction of the data sources.

Underlying paper: cvml.ist.ac.at/papers/konstantinov-icml2020.pdf

 

The talk also can be joined online via our ZOOM MEETING: univienna.zoom.us/j/66251112914

Meeting room opens at: June 12, 2023, 4.30 pm Vienna

Meeting ID: 662 5111 2914

Password: 013246

Zur Webseite der Veranstaltung

---

Veranstalter

Institut für Statistik und Operations Research

---

Kontakt

Sabine Sobotka-Tompits, BA
Fakultät für Wirtschaftswissenschaften
Institut für Statistik und Operations Research
+43 1 4277 38631
sabine.sobotka-tompits@univie.ac.at

Erstellt am Freitag, 19. Mai 2023, 13:27
Letzte Änderung am Mittwoch, 07. Juni 2023, 14:14