Brian Lu

icon location PhD student in NLP.

Results 2 comments of Brian Lu

Scaling the hessian by learning rate

Hi Jon, Thanks for the detailed explanation - makes a lot of sense now! > In fact, when you write them out they are the same on a quadratic objective....

Why does JoinFn use Formulas.lambdaApply instead of Formulas.betaReduce?

Thanks for the quick comment, and yes, wrapping `Formulas.lambdaApply` (in `JoinFn`) inside `Formulas.betaReduction` would solve the problem. However, I'm not entirely sure whether this is a bug or whether there...