Skip to main content

Timeline for Uniform Convergence for Vectors

Current License: CC BY-SA 3.0

13 events
when toggle format what by license comment
Nov 28, 2017 at 13:21 comment added Aryeh Kontorovich @omerbp I think I have a fix.
Nov 28, 2017 at 13:20 history edited Aryeh Kontorovich CC BY-SA 3.0
added 1200 characters in body
Nov 28, 2017 at 10:07 comment added AvidLearner Not sure it helps, but $g$ is defined over the set of binary vectors only.
Nov 28, 2017 at 9:57 comment added Aryeh Kontorovich You're right -- see my edit.
Nov 28, 2017 at 9:56 history edited Aryeh Kontorovich CC BY-SA 3.0
added 234 characters in body
Nov 27, 2017 at 23:44 comment added AvidLearner I probably miss something. How can one, using the first display and the empirical distribution analog, bound $||L_D(f)-\hat L_S(f)||$ using the $\tilde f$ equivalents ? I would appreciate if you could provide the claims for bounding $||L_D(f)-\hat L_S(f)||$ using $L_D(\tilde f),\hat L_S(\tilde f)$. Sorry for being blind here....
Nov 27, 2017 at 11:50 history edited Aryeh Kontorovich CC BY-SA 3.0
added 1 character in body
Nov 27, 2017 at 10:41 comment added Aryeh Kontorovich ... as in that first display.
Nov 27, 2017 at 10:40 comment added Aryeh Kontorovich Because f is sandwiched between 1/2 tilde f and tilde f.
Nov 27, 2017 at 10:37 comment added AvidLearner Could you please elaborate on why the last inequality holds for $f$? I can only see why it holds for $\tilde f$...
Nov 27, 2017 at 10:35 comment added Aryeh Kontorovich It was used to establish the first large-display inequality.
Nov 27, 2017 at 9:08 comment added AvidLearner Thanks for the response. I can see why the last inequality holds if we replace $f$ with $\tilde f$ (as the text just above the inequality explains), but I fail to see why the inequality holds as you wrote it . Where did you use $\frac12\tilde g\le g\le\tilde g$?
Nov 22, 2017 at 19:44 history answered Aryeh Kontorovich CC BY-SA 3.0