Sciweavers

16 search results - page 3 / 4
» No-regret learning in convex games
Sort
View
SIAMJO
2008
104views more  SIAMJO 2008»
13 years 6 months ago
A Minimax Theorem with Applications to Machine Learning, Signal Processing, and Finance
This paper concerns a fractional function of the form xT a/ xT Bx, where B is positive definite. We consider the game of choosing x from a convex set, to maximize the function, an...
Seung-Jean Kim, Stephen P. Boyd
ML
2010
ACM
138views Machine Learning» more  ML 2010»
13 years 1 months ago
Mining adversarial patterns via regularized loss minimization
Traditional classification methods assume that the training and the test data arise from the same underlying distribution. However, in several adversarial settings, the test set is...
Wei Liu, Sanjay Chawla
ICML
2007
IEEE
14 years 7 months ago
Efficiently computing minimax expected-size confidence regions
Given observed data and a collection of parameterized candidate models, a 1- confidence region in parameter space provides useful insight as to those models which are a good fit t...
Brent Bryan, H. Brendan McMahan, Chad M. Schafer, ...
NIPS
2008
13 years 7 months ago
On the Efficient Minimization of Classification Calibrated Surrogates
Bartlett et al (2006) recently proved that a ground condition for convex surrogates, classification calibration, ties up the minimization of the surrogates and classification risk...
Richard Nock, Frank Nielsen
COLT
2004
Springer
13 years 11 months ago
Deterministic Calibration and Nash Equilibrium
Abstract. We provide a natural learning process in which the joint frequency of empirical play converges into the set of convex combinations of Nash equilibria. In this process, al...
Sham Kakade, Dean P. Foster