Re:New finding: 600M years ago, a single mutation changed ev...
by hiddencost on Monday January 11, 2016 @07:07PM
(#10884643)
Your statement is true-ish, but not true enough.
It is true there are more local minima, but they're generally pretty equivalent. In fact, in high dimensions, saddle points are a much bigger problem than local minima. [0] The fact that optimization works on these large, non-convex problems is kind of a marvel, and raises really interesting questions. (mostly "this shouldn't work this well unless there's some kind of regularity to these problems that makes them nicely behaved"). What this says about evolution I neither know nor care to speculate (above my pay grade).
It is true there are more local minima, but they're generally pretty equivalent. In fact, in high dimensions, saddle points are a much bigger problem than local minima. [0] The fact that optimization works on these large, non-convex problems is kind of a marvel, and raises really interesting questions. (mostly "this shouldn't work this well unless there's some kind of regularity to these problems that makes them nicely behaved"). What this says about evolution I neither know nor care to speculate (above my pay grade).
[0] http://arxiv.org/abs/1406.2572
Yes, the backpropaganda can get annoying.