Search Results for author:
Found 16 papers, 2 papers with code
Game Mining: How to Make Money from those about to Play a Game
It is known that a player in a noncooperative game can benefit by publicly restricting his possible moves before play begins.
What can we know about that which we cannot even imagine?
In this essay I will consider a sequence of questions.
The Implications of the No-Free-Lunch Theorems for Meta-induction
Here I review the NFL theorems, emphasizing that they do not only concern the case where there is a uniform prior -- they prove that there are "as many priors" (loosely speaking) for which any induction algorithm $A$ out-generalizes some induction algorithm $B$ as vice-versa.
Thermodynamic Uncertainty Relations for Multipartite Processes
After deriving these extended TURs we use them to obtain bounds that do not involve the global EP, but instead relate the local EPs of the individual systems and the statistical coupling among the currents generated within those systems.
Statistical Mechanics
Noisy Deductive Reasoning: How Humans Construct Math, and How Math Constructs Universes
We present a computational model of mathematical reasoning according to which mathematics is a fundamentally stochastic process.
What is important about the No Free Lunch theorems?
The No Free Lunch theorems prove that under a uniform distribution over induction problems (search problems or learning problems), all induction algorithms perform equally.
Minimal entropy production due to constraints on rate matrix dependencies in multipartite processes
I consider multipartite processes in which there are constraints on each subsystem's rate matrix, restricting which other subsystems can directly affect its dynamics.
Uncertainty relations and fluctuation theorems for Bayes nets
I derive fluctuation theorems governing the entropy production (EP)of arbitrary sets of the systems in such a Bayes net.
Upgrading from Gaussian Processes to Student's-T Processes
The Student's-T distribution has higher Kurtosis than a Gaussian distribution and so outliers are much more likely, and the posterior variance increases or decreases depending on the variance of observed data sample values.
Nonlinear Information Bottleneck
Information bottleneck (IB) is a technique for extracting information in one random variable $X$ that is relevant for predicting another random variable $Y$.
Bayesian Optimization with a Finite Budget: An Approximate Dynamic Programming Approach
We consider the problem of optimizing an expensive objective function when a finite budget of total evaluations is prescribed.
Reducing the error of Monte Carlo Algorithms by Learning Control Variates
Crucially, it is a post-processing technique, requiring no additional samples, and can be applied to data generated by any MC estimator.
Optimal high-level descriptions of dynamical systems
These include SSC as a measure of the complexity of a dynamical system, and as a way to quantify information flow between the scales of a system.
Predicting the behavior of interacting humans by fusing data from multiple sources
Multi-fidelity methods combine inexpensive low-fidelity simulations with costly but highfidelity simulations to produce an accurate model of a system of interest at minimal cost.
Estimating Functions of Probability Distributions from a Finite Set of Samples, Part 1: Bayes Estimators and the Shannon Entropy
We present estimators for entropy and other functions of a discrete probability distribution when the data is a finite sample drawn from that probability distribution.
