• Publications
  • Influence
Searching in the presence of linearly bounded errors
TLDR
We consider the problem of determining an unknown quantity x by asking “yes-no” questions, where some of the answers may be erroneous. Expand
  • 89
  • 5
  • PDF
PAC learning with irrelevant attributes
TLDR
We consider the problem of learning in the presence of irrelevant attributes in Valiant's PAC model (1984). Expand
  • 45
  • 3
On playing “Twenty Questions” with a liar
TLDR
We consider a version of the game “Twenty Questions” played on the set {0,…,N-1} where the player giving answers may lie in her answers, for some fixed and previously known fraction of the answers. Expand
  • 77
  • 1
  • PDF
On-Line Algorithms for 2-Coloring Hypergraphs Via Chip Games
TLDR
We show constructive upper and lower bounds on the number of edges of a hypergraph which allow it to be 2-colored on-line . Expand
  • 11
  • PDF
Searching in the presence of errors
We consider the problem of searching for a quantity x in a discrete, bounded domain (e.g. $\{$1, ...,$n\}$) by asking "yes-no" questions, when some of the answers received may be lies. In particular,Expand
  • 2
Notes on Learning with Irrelevant Attributes in the PAC Model
In these notes, we sketch some of our work on learning with irrelevant attributes in Valiant’s PAC model [V84]. In the PAC model, the goal of the learner is to produce an approximately correctExpand