Zoom Logo

PhDOpen: Aleksander Mądry - Shared screen with speaker view
Krzysztof Galias
26:47
but the accuracy on this robustified dataset will be lower than accuracy on non-robust one, right?
jakub
52:46
Does this mean that when the robust models are wrong are they usually more "sensibly" wrong?
Krzysztof Galias
01:22:50
great lectures! do you know of any work being done in the context of "robust" reinforcement learning, especially exploring phenomena qualitatively different from the supervised setting?
piotrnawrot
01:24:16
great lectures, I learned a lot, thank you!
Przemek Kaleta
01:29:03
Thank you!