• Publications
  • Influence
Learnability and the Vapnik-Chervonenkis dimension
Valiant's learnability model is extended to learning classes of concepts defined by regions in Euclidean space En. The methods in this paper lead to a unified treatment of some of Valiant's results,Expand
  • 1,802
  • 173
  • Open Access
Exponentiated Gradient Versus Gradient Descent for Linear Predictors
We consider two algorithm for on-line prediction based on a linear model. The algorithms are the well-known Gradient Descent (GD) algorithm and a new algorithm, which we call EG(+/-). They bothExpand
  • 853
  • 80
  • Open Access
The Weighted Majority Algorithm
We study the construction of prediction algorithms in a situation in which a learner faces a sequence of trials, with a prediction to be made in each, and the goal of the learner is to make fewExpand
  • 1,216
  • 69
  • Open Access
How to use expert advice
We analyze algorithms that predict a binary value by combining the predictions of several prediction strategies, called `experts''. Our analysis is for worst-case situations, i.e., we make noExpand
  • 594
  • 46
  • Open Access
Tracking the Best Expert
We generalize the recent worst-case loss bounds for on-line algorithms where the additional loss of the algorithm on the whole sequence of examples over the loss of the best expert is bounded. TheExpand
  • 239
  • 43
On-Line Portfolio Selection Using Multiplicative Updates
We present an on-line investment algorithm that achieves almost the same wealth as the best constant-rebalanced portfolio determined in hindsight from the actual market outcomes. The algorithmExpand
  • 272
  • 37
  • Open Access
Relating Data Compression and Learnability
We explore the learnability of two-valued functions from samples using the paradigm of Data Compression. A first algorithm (compression) choses a small subset of the sample which is called theExpand
  • 222
  • 37
  • Open Access
Occam's Razor
Abstract We show that a polynomial learning algorithm, as defined by Valiant (1984), is obtained whenever there exists a polynomial-time method of producing, for any sequence of observations, aExpand
  • 657
  • 29
Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions
We consider on-line density estimation with a parameterized density from the exponential family. The on-line algorithm receives one example at a time and maintains a parameter that is essentially anExpand
  • 249
  • 29
  • Open Access
Tracking the Best Expert
AbstractWe generalize the recent relative loss bounds for on-line algorithms where the additional loss of the algorithm on the whole sequence of examples over the loss of the best expert is bounded.Expand
  • 273
  • 28
  • Open Access