Asymptotic Theory of Information-Theoretic Experimental Design

Authors:
Liam Paninski
Affiliations:
Gatsby Computational Neuroscience Unit, University College London, London, WC1N 3AR, U.K.
Venue:
Neural Computation
Year:
2005

Citing 5
Cited 7

Asymptotic theory of finite dimensional normed spaces

Asymptotic theory of finite dimensional normed spaces
Elements of information theory

Elements of information theory
Information-based objective functions for active data selection

Neural Computation
Selective Sampling Using the Query by Committee Algorithm

Machine Learning
Active learning with statistical models

Journal of Artificial Intelligence Research

Near-Optimal Sensor Placements in Gaussian Processes: Theory, Efficient Algorithms and Empirical Studies

The Journal of Machine Learning Research
Sequential optimal design of neurophysiology experiments

Neural Computation
How to modify a neural network gradually without changing its input-output functionality

Neural Computation
Adaptive design optimization: A mutual information-based approach to model discrimination in cognitive science

Neural Computation
Information theory in neuroscience

Journal of Computational Neuroscience
Automating the design of informative sequences of sensory stimuli

Journal of Computational Neuroscience
Active data collection for efficient estimation and comparison of nonlinear neural models

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We discuss an idea for collecting data in a relatively efficient manner. Our point of view is Bayesian and information-theoretic: on any given trial, we want to adaptively choose the input in such a way that the mutual information between the (unknown) state of the system and the (stochastic) output is maximal, given any prior information (including data collected on any previous trials). We prove a theorem that quantifies the effectiveness of this strategy and give a few illustrative examples comparing the performance of this adaptive technique to that of the more usual nonadaptive experimental design. In particular, we calculate the asymptotic efficiency of the information-maximization strategy and demonstrate that this method is in a well-defined sense never less efficient—and is generically more efficient—than the nonadaptive strategy. For example, we are able to explicitly calculate the asymptotic relative efficiency of the staircase method widely employed in psychophysics research and to demonstrate the dependence of this efficiency on the form of the psychometric function underlying the output responses.