SERVING THE QUANTITATIVE FINANCE COMMUNITY

katastrofa
Posts: 9342
Joined: August 16th, 2007, 5:36 am
Location: Alpha Centauri

### Re: Hacking ML for fun & profit

That was my point. Equating gradient methods to simulated annealing (artificial time vs artificial temperature) is not a far jump, but in the wrong dimension. Physicists developed those methods and name things like that for a reason

Cuchulainn
Posts: 62424
Joined: July 16th, 2004, 7:38 am
Location: Amsterdam
Contact:

### Re: Hacking ML for fun & profit

That was my point. Equating gradient methods to simulated annealing (artificial time vs artificial temperature) is not a far jump, but in the wrong dimension. Physicists developed those methods and name things like that for a reason
Maybe the variable $t$ causes confusion. Better to say $T = T(t)$ and then you get a double whammy. A kind of 1:1 correspondence.

katastrofa
Posts: 9342
Joined: August 16th, 2007, 5:36 am
Location: Alpha Centauri

### Re: Hacking ML for fun & profit

*groans*

Cuchulainn
Posts: 62424
Joined: July 16th, 2004, 7:38 am
Location: Amsterdam
Contact:

### Re: Hacking ML for fun & profit

That's not a groan, it's a snarl