front mathematics

5 events

when toggle format	what		by	license	comment
Jul 22, 2014 at 19:19	comment	added	Suvrit		@RHahn: actually you'd be surprised; knowledge of measure theory is useful in ML research; see e.g., arxiv.org/abs/1202.6504, arxiv.org/abs/0907.5309, amongst many others.
Jul 22, 2014 at 18:55	comment	added	R Hahn		Regarding 1, I'd say that measure theory would mainly be a distraction in a ML context. In general, mathematical topics that lend themselves to computer implementation are most helpful. For example, in terms of functional analysis, an existence proof that some function can be approximated in some basis is much more useful if it is constructive. This amplifies Suvrit's comment that numerical linear algebra is often more useful than abstract linear algebra.
Jul 22, 2014 at 18:12	comment	added	Matthias Wendt		Maybe it is worth mentioning the statistical manifolds stuff of Amari, also called information geometry. Viewing families of probability distributions as Riemannian manifolds has helped clarify some statistical concepts. I specifically remember papers analyzing the EM-type algorithms from the information-geometry point of view.
Jul 22, 2014 at 16:47	comment	added	Suvrit		This answer is a work in progress; I'll improve it with references to books and papers to make it more useful, as soon as I get a chance
Jul 22, 2014 at 16:46	history	answered	Suvrit	CC BY-SA 3.0