Zestyclose_Speed3349

joined 1 year ago
[โ€“] Zestyclose_Speed3349@alien.top 1 points 1 year ago (1 children)

It depends on the field. In DL repeating the training procedure N times may be very costly which is unfortunate. In RL it's common to repeat the experiments 25-100 times and report standard error.

[โ€“] Zestyclose_Speed3349@alien.top 1 points 1 year ago (1 children)

Measure theory, differential geometry and optimal transport are great fields if you are going for theoretical ML.