29 hasil untuk "Hutter, Marcus"
Menampilkan 1–20 · 0,22 detik · RSS
-
Artikel Jurnal Teks lengkap
Modeling the Arrows of Time with Causal Multibaker Maps
Why do we remember the past, and plan the future? We introduce a toy model in which to investigate emergent time asymmetries: the causal multibaker maps. These are reversible discrete-time dynamical systems with configurable causal interactions. Imposing a suitable initial condition or “Past…
-
Artikel Jurnal Teks lengkap
Simplicity and Complexity in Combinatorial Optimization
Many problems in physics and computer science can be framed in terms of combinatorial optimization. Due to this, it is interesting and important to study theoretical aspects of such optimization. Here, we study connections between Kolmogorov complexity, optima, and optimization. We argue that (1)…
-
Preprint Teks lengkap
New Error Bounds for Solomonoff Prediction
Solomonoff sequence prediction is a scheme to predict digits of binary strings without knowing the underlying probability distribution. We call a prediction scheme informed when it knows the true probability distribution of the sequence. Several new relations between universal Solomonoff sequence…
-
Preprint Teks lengkap
Proton Spin in the Instanton Background
The proton form factors are reduced to vacuum correlators of 4 quark fields by assuming independent constituent quarks. The axial singlet quark and gluonic form factors are calculated in the instanton liquid model. A discussion of gauge(in)dependence is given.
-
Preprint Teks lengkap
Self-Optimizing and Pareto-Optimal Policies in General Environments based on Bayes-Mixtures
The problem of making sequential decisions in unknown probabilistic environments is studied. In cycle $t$ action $y_t$ results in perception $x_t$ and reward $r_t$, where all quantities in general may depend on the complete history. The perception $x_t$ and reward $r_t$ are sampled from the…
-
Preprint Teks lengkap
The Fastest and Shortest Algorithm for All Well-Defined Problems
An algorithm $M$ is described that solves any well-defined problem $p$ as quickly as the fastest algorithm computing a solution to $p$, save for a factor of 5 and low-order additive terms. $M$ optimally distributes resources between the execution of provably correct $p$-solving programs and an…
-
Preprint Teks lengkap
Instantons in QCD: Theory and Application of the Instanton Liquid Model
Numerical and anaytical studies of the instanton liquid model have allowed the determination of many hadronic parameters during the last 13 years. Most part of this thesis is devoted to the extension of the analytical methods. The meson correlation (polarization) functions are calculated in the…
-
Preprint Teks lengkap
An effective Procedure for Speeding up Algorithms
The provably asymptotically fastest algorithm within a factor of 5 for formally described problems will be constructed. The main idea is to enumerate all programs provably equivalent to the original problem by enumerating all proofs. The algorithm could be interpreted as a generalization and…
-
Preprint Teks lengkap
Fitness Uniform Selection to Preserve Genetic Diversity
In evolutionary algorithms, the fitness of a population increases with time by mutating and recombining individuals and by a biased selection of more fit individuals. The right selection pressure is critical in ensuring sufficient optimization progress on the one hand and in preserving genetic…
-
Preprint Teks lengkap
Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences
Solomonoff's uncomputable universal prediction scheme $ξ$ allows to predict the next symbol $x_k$ of a sequence $x_1...x_{k-1}$ for any Turing computable, but otherwise unknown, probabilistic environment $μ$. This scheme will be generalized to arbitrary environmental classes, which, among others…
-
Preprint Teks lengkap
Universal Sequential Decisions in Unknown Environments
We give a brief introduction to the AIXI model, which unifies and overcomes the limitations of sequential decision theory and universal Solomonoff induction. While the former theory is suited for active agents in known environments, the latter is suited for passive prediction of unknown…
-
Preprint Teks lengkap
Optimality of Universal Bayesian Sequence Prediction for General Loss and Alphabet
Various optimality properties of universal sequence predictors based on Bayes-mixtures in general, and Solomonoff's prediction scheme in particular, will be studied. The probability of observing $x_t$ at time $t$, given past observations $x_1...x_{t-1}$ can be computed with the chain rule if the…
-
Preprint Teks lengkap
Value Under Ignorance in Universal Artificial Intelligence
We generalize the AIXI reinforcement learning agent to admit a wider class of utility functions. Assigning a utility to each possible interaction history forces us to confront the ambiguity that some hypotheses in the agent's belief distribution only predict a finite prefix of the history, which is…
-
Preprint Teks lengkap
Adaptive Online Prediction by Following the Perturbed Leader
When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the analysis of Weighted Majority derivatives quite complicated. In particular, for arbitrary weights there have been no…
-
Preprint Teks lengkap
Bayesian Treatment of Incomplete Discrete Data applied to Mutual Information and Feature Selection
Given the joint chances of a pair of random variables one can compute quantities of interest, like the mutual information. The Bayesian treatment of unknown chances involves computing, from a second order prior distribution and the data likelihood, a posterior distribution of the chances. A common…
-
Preprint Teks lengkap
Prediction with Expert Advice by Following the Perturbed Leader for General Weights
When applying aggregating strategies to Prediction with Expert Advice, the learning rate must be adaptively tuned. The natural choice of sqrt(complexity/current loss) renders the analysis of Weighted Majority derivatives quite complicated. In particular, for arbitrary weights there have been no…
-
Preprint Teks lengkap
Master Algorithms for Active Experts Problems based on Increasing Loss Values
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 slowly. We prove loss bounds…
-
Preprint Teks lengkap
Fitness Uniform Deletion: A Simple Way to Preserve Diversity
A commonly experienced problem with population based optimisation methods is the gradual decline in population diversity that tends to occur over time. This can slow a system's progress or even halt it completely if the population converges on a local optimum from which it cannot escape. In this…
-
Preprint Teks lengkap
Defensive Universal Learning with Experts
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…
-
Preprint Teks lengkap
Universal Learning of Repeated Matrix Games
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…