# Manfred K. Warmuth

Author pages are created from data sourced from our academic publisher partnerships and public sources.

- Publications
- Influence

Learnability and the Vapnik-Chervonenkis dimension

- A. Blumer, A. Ehrenfeucht, D. Haussler, Manfred K. Warmuth
- Mathematics, Computer Science
- JACM
- 1 October 1989

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

Exponentiated Gradient Versus Gradient Descent for Linear Predictors

- Jyrki Kivinen, Manfred K. Warmuth
- Mathematics, Computer Science
- Inf. Comput.
- 10 January 1997

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 both… Expand

The Weighted Majority Algorithm

- N. Littlestone, Manfred K. Warmuth
- Mathematics, Computer Science
- Inf. Comput.
- 1 February 1994

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 few… Expand

How to use expert advice

- N. Cesa-Bianchi, Y. Freund, D. Helmbold, D. Haussler, R. Schapire, Manfred K. Warmuth
- Computer Science
- STOC '93
- 1 June 1993

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 no… Expand

Tracking the Best Expert

- M. Herbster, Manfred K. Warmuth
- Mathematics, Computer Science
- ICML
- 9 July 1995

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. The… Expand

On-Line Portfolio Selection Using Multiplicative Updates

- D. Helmbold, R. Schapire, Y. Singer, Manfred K. Warmuth
- Computer Science, Economics
- ICML
- 1 October 1998

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 algorithm… Expand

Relating Data Compression and Learnability

- N. Littlestone, Manfred K. Warmuth
- Computer Science
- 2003

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 the… Expand

- 222
- 37
- Open Access

Occam's Razor

- A. Blumer, A. Ehrenfeucht, D. Haussler, Manfred K. Warmuth
- Mathematics, Computer Science
- Inf. Process. Lett.
- 6 April 1987

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, a… Expand

Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions

- Katy S. Azoury, Manfred K. Warmuth
- Mathematics, Computer Science
- Machine Learning
- 30 July 1999

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 an… Expand

Tracking the Best Expert

- M. Herbster, Manfred K. Warmuth
- Mathematics, Computer Science
- Machine Learning
- 1 August 1998

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