Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Grunwald, Peter D"'
Publikováno v:
NeurIPS 2019
We present a new PAC-Bayesian generalization bound. Standard bounds contain a $\sqrt{L_n \cdot \KL/n}$ complexity term which dominates unless $L_n$, the empirical error of the learning algorithm's randomized predictions, vanishes. We manage to replac
Externí odkaz:
http://arxiv.org/abs/1905.13367
Autor:
Grunwald, Peter D., Halpern, Joseph Y.
As examples such as the Monty Hall puzzle show, applying conditioning to update a probability distribution on a ``naive space', which does not take into account the protocol used, can often lead to counterintuitive results. Here we examine why. A cri
Externí odkaz:
http://arxiv.org/abs/1407.7183
Autor:
Grunwald, Peter D., Halpern, Joseph Y.
We consider how an agent should update her uncertainty when it is represented by a set P of probability distributions and the agent observes that a random variable X takes on value x, given that the agent makes decisions using the minimax criterion,
Externí odkaz:
http://arxiv.org/abs/1407.7190
Autor:
Grunwald, Peter D., Halpern, Joseph Y.
It is commonly-accepted wisdom that more information is better, and that information should never be ignored. Here we argue, using both a Bayesian and a non-Bayesian analysis, that in some situations you are better off ignoring information if your un
Externí odkaz:
http://arxiv.org/abs/1407.7188
Autor:
Grunwald, Peter D, Halpern, Joseph Y
Publikováno v:
Journal Of Artificial Intelligence Research, Volume 42, pages 393-426, 2011
We consider how an agent should update her beliefs when her beliefs are represented by a set P of probability distributions, given that the agent makes decisions using the minimax criterion, perhaps the best-studied and most commonly-used criterion i
Externí odkaz:
http://arxiv.org/abs/1401.3906
We analyze differences between two information-theoretically motivated approaches to statistical inference and model selection: the Minimum Description Length (MDL) principle, and the Minimum Message Length (MML) principle. Based on this analysis, we
Externí odkaz:
http://arxiv.org/abs/1301.7378
Autor:
Grunwald, Peter D.
We give an interpretation of the Maximum Entropy (MaxEnt) Principle in game-theoretic terms. Based on this interpretation, we make a formal distinction between different ways of {em applying/} Maximum Entropy distributions. MaxEnt has frequently been
Externí odkaz:
http://arxiv.org/abs/1301.3860
Consider the set of all sequences of $n$ outcomes, each taking one of $m$ values, that satisfy a number of linear constraints. If $m$ is fixed while $n$ increases, most sequences that satisfy the constraints result in frequency vectors whose entropy
Externí odkaz:
http://arxiv.org/abs/1107.6004
We introduce algorithmic information theory, also known as the theory of Kolmogorov complexity. We explain the main concepts of this quantitative approach to defining `information'. We discuss the extent to which Kolmogorov's and Shannon's informatio
Externí odkaz:
http://arxiv.org/abs/0809.2754
Autor:
Grunwald, Peter D., Halpern, Joseph Y.
We consider how an agent should update her uncertainty when it is represented by a set $\P$ of probability distributions and the agent observes that a random variable $X$ takes on value $x$, given that the agent makes decisions using the minimax crit
Externí odkaz:
http://arxiv.org/abs/0711.3235