[CSDM] [pvsnp-all] [Theory-Read] Theory lunch tomorrow @noon

Mark Braverman mbraverm at CS.Princeton.EDU
Wed Jun 19 11:23:13 EDT 2013


Reminder!

----- Original Message -----
From: "Mark Braverman" <mbraverm at CS.Princeton.EDU>
To: theory-read at lists.cs.princeton.edu, "expeditions project list" <pvsnp-all at lists.cs.princeton.edu>
Cc: bjuba at alum.mit.edu
Sent: Tuesday, June 18, 2013 2:24:05 PM
Subject: [Theory-Read] Theory lunch tomorrow @noon

Time: tomorrow, Wed June 19 @noon
Location: CS Building Room 302

Speaker: Brendan Juba, Harvard University

Efficient reasoning in PAC Semantics

Machine learning is often employed as one step in a larger application, serving to perform information extraction or data mining for example. The rules obtained by such learning are then used as inputs to a further analysis. As a consequence of the inputs to this analysis having been learned, however, its conclusions can only be theoretically guaranteed to satisfy the same standard as the inputs---that of "PAC Semantics" (Valiant, 2000). In this talk, we explore the benefits of taking the problems of learning and logical reasoning together, capturing a relatively general family of such applications. Briefly, the benefit is that we can simultaneously (1) handle incomplete information, (2) utilize rules that are a reasonable but imperfect fit for the data, and (3) reach conclusions more efficiently than is achieved by known algorithms for reasoning from rules alone. Precisely, we consider a problem of testing the validity of a "query" formula (hypothesis) against incomplete dat
 a. We present algorithms for soundly verifying such queries that succeed whenever there exist learnable rules that suffice to complete a simple proof of the query, matching what can be achieved by such a two-stage learning and reasoning process.
_______________________________________________
Theory-Read mailing list
Theory-Read at lists.cs.princeton.edu
https://lists.cs.princeton.edu/mailman/listinfo/theory-read
_______________________________________________
pvsnp-all mailing list
pvsnp-all at lists.cs.princeton.edu
https://lists.cs.princeton.edu/mailman/listinfo/pvsnp-all



More information about the csdm mailing list