Sciweavers

77 search results - page 4 / 16
» Sample Size Lower Bounds in PAC Learning by Algorithmic Comp...
Sort
View
ICML
2004
IEEE
14 years 8 months ago
Communication complexity as a lower bound for learning in games
A fast-growing body of research in the AI and machine learning communities addresses learning in games, where there are multiple learners with different interests. This research a...
Vincent Conitzer, Tuomas Sandholm
COCO
2005
Springer
150views Algorithms» more  COCO 2005»
14 years 1 months ago
The Quantum Adversary Method and Classical Formula Size Lower Bounds
We introduce two new complexity measures for Boolean functions, which we name sumPI and maxPI. The quantity sumPI has been emerging through a line of research on quantum query com...
Sophie Laplante, Troy Lee, Mario Szegedy
ECCC
2010
124views more  ECCC 2010»
13 years 7 months ago
Lower Bounds and Hardness Amplification for Learning Shallow Monotone Formulas
Much work has been done on learning various classes of "simple" monotone functions under the uniform distribution. In this paper we give the first unconditional lower bo...
Vitaly Feldman, Homin K. Lee, Rocco A. Servedio
COLT
2001
Springer
13 years 12 months ago
Smooth Boosting and Learning with Malicious Noise
We describe a new boosting algorithm which generates only smooth distributions which do not assign too much weight to any single example. We show that this new boosting algorithm ...
Rocco A. Servedio
STOC
2012
ACM
196views Algorithms» more  STOC 2012»
11 years 10 months ago
Time-space tradeoffs in resolution: superpolynomial lower bounds for superlinear space
We give the first time-space tradeoff lower bounds for Resolution proofs that apply to superlinear space. In particular, we show that there are formulas of size N that have Reso...
Paul Beame, Christopher Beck, Russell Impagliazzo