Tyrrell_McAllister comments on Nonparametric Ethics - Less Wrong

27 Post author: Eliezer_Yudkowsky 20 June 2009 11:31AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (56)

You are viewing a single comment's thread. Show more comments above.

Comment author: Tyrrell_McAllister 21 June 2009 03:26:36PM 1 point [-]

Thanks, Steve. So, can I unpack Eliezer's condition

we think that the true values at nearby positions are likely to be similar

as saying of the true values that there might be switchpoints, but most points aren't switchpoints?

Comment author: Eliezer_Yudkowsky 21 June 2009 04:31:37PM 1 point [-]

Yes, and in the limit of obtaining more data indefinitely, the in-between regions will shrink indefinitely (at least if you're using k-nearest-neighbors and not smooth kernels).

Comment author: Steve_Rayhawk 21 June 2009 04:21:24PM 1 point [-]

Yes, switchpoints or large smooth jumps.