Measure theory, differential geometry and optimal transport are great fields if you are going for theoretical ML.
Zestyclose_Speed3349
joined 1 year ago
Measure theory, differential geometry and optimal transport are great fields if you are going for theoretical ML.
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.