#### Filter Results:

- Full text PDF available (35)

#### Publication Year

1976

2017

#### Publication Type

#### Co-author

#### Publication Venue

#### Key Phrases

Learn More

- Marcus Hutter, Jan Poland
- Journal of Machine Learning Research
- 2005

When applying aggregating strategies to Prediction with Expert Advice , the learning rate must be adaptively tuned. The natural choice of complexity/current loss renders the analysis of Weighted Majority derivatives quite complicated. In particular, for arbitrary weights there have been no results proven so far. The analysis of the alternative " Follow the… (More)

- Marcus Hutter, Jan Poland
- ALT
- 2004

When applying aggregating strategies to Prediction with Expert Advice , the learning rate must be adaptively tuned. The natural choice of complexity/current loss renders the analysis of Weighted Majority derivatives quite complicated. In particular, for arbitrary weights there have been no results proven so far. The analysis of the alternative " Follow the… (More)

- Jan Poland
- SAGA
- 2005

A main problem of " Follow the Perturbed Leader " strategies for online decision problems is that regret bounds are typically proven against oblivious adversary. In partial observation cases, it was not clear how to obtain performance guarantees against adaptive adversary, without worsening the bounds. We propose a conceptually simple argument to resolve… (More)

- Igor Fischer, Jan Poland
- 2004

Switzerland (SUPSI), and was founded in 1988 by the Dalle Molle Foundation which promoted quality of life. Abstract Analyzing the affinity matrix spectrum is an increasingly popular data clustering method. We propose three new algorithmic components which are appropriate for improving performance of spectral clustering. First, observing the eigenvectors… (More)

- Jan Poland, Marcus Hutter
- IEEE Transactions on Information Theory
- 2005

Minimum description length (MDL) is an important principle for induction and prediction, with strong relations to optimal Bayesian learning. This paper deals with learning processes which are independent and identically distributed (i.i.d.) by means of two-part MDL, where the underlying model class is countable. We consider the online learning framework,… (More)

- Jan Poland, Marcus Hutter
- ALT
- 2005

This paper shows how universal learning can be achieved with expert advice. To this aim, we specify an experts algorithm with the following characteristics: (a) it uses only feedback from the actions actually chosen (bandit setup), (b) it can be applied with countably infinite expert classes, and (c) it copes with losses that may grow in time appropriately… (More)

- Jan Poland, Andreas Zell
- 2001

The covariance matrix adaptation (CMA) is one of the most powerful self adaptation mechanisms for Evolution Strategies. However, for increasing search space dimension N , the performance declines, since the CMA has space and time complexity O(N 2). Adapting the main mutation vector instead of the covariance matrix yields an adaptation mechanism with space… (More)

- Jan Poland, Marcus Hutter
- COLT
- 2004

We study the properties of the Minimum Description Length principle for sequence prediction, considering a two-part MDL estimator which is chosen from a countable class of models. This applies in particular to the important case of universal sequence prediction, where the model class corresponds to all algorithms for some fixed universal Turing machine… (More)

- Jan Poland, Marcus Hutter
- ALT
- 2004

Switzerland (SUPSI), and was founded in 1988 by the Dalle Molle Foundation which promoted quality of life. Abstract We consider the Minimum Description Length principle for online sequence prediction. If the underlying model class is discrete, then the total expected square loss is a particularly interesting performance measure: (a) this quantity is… (More)

- Jan Poland, Marcus Hutter
- ArXiv
- 2005

We study and compare the learning dynamics of two universal learning algorithms, one based on Bayesian learning and the other on prediction with expert advice. Both approaches have strong asymptotic performance guarantees. When confronted with the task of finding good long-term strategies in repeated 2 × 2 matrix games, they behave quite differently.