Logo

Sanmi Koyejo theory ML talk - Shared screen with speaker view
Jonathan Rosenfeld
34:45
is there anything preventing us running GD )as opposed to SGD) on non-average decomposing measures - e.g. F measure?
Jonathan Rosenfeld
37:35
thank you!
Jonathan Rosenfeld
01:09:31
sorry for the silly question: linear post processing means an afine function of TP, TN? so F measures are not linear?
Jonathan Rosenfeld
01:11:45
Thanks. the followup then becomes - how does one find the equivalent measure in practice (since the distribution is not known in advance)
Boaz Barak
01:13:35
Feel free to unmute and ask if this discussion didn't answer it
Jonathan Rosenfeld
01:13:57
thank you! I’ll let it marinate a bit .
Jonathan Rosenfeld
02:01:51
Thank you!!