Machine learning
You increase the batch size from 32 to 512 without changing anything else. What happens?
AdvancedMultiple choice
You increase the batch size from 32 to 512 without changing anything else. What happens?
- AGradient noise falls fourfold, so the learning rate usually has to rise to compensate
- BTraining becomes strictly better, since the gradient is more accurate
- CNothing changes, since the expected gradient is the same
- DConvergence slows in wall-clock time on any hardware
The worked solution is in Premium
The answer, the full working and the one idea to take away – for this and all 1,322 questions in the bank. Answer it in practice and your working is marked, with a known mistake named when you make one.
Report an issue with this question
Learn the method
Of the kind reported at
More machine learning questions
- A quadratic loss has Hessian eigenvalues 4 and 0.5.Applied · Premium
- One step of gradient descent, part 2 of 4Applied · Premium
- Adam’s first-moment estimate starts at 0 with β₁ = 0.9.Advanced · Premium
- One step of gradient descent, part 3 of 4Advanced · Premium
- One step of gradient descent, part 4 of 4Expert · Premium
- One step of gradient descent, part 1 of 4Foundation · Premium