On the complexity of inductive inference
Information and Control
On the role of procrastination in machine learning
Information and Computation
Machine Learning
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
The Design and Analysis of Computer Algorithms
The Design and Analysis of Computer Algorithms
Pattern Classification (2nd Edition)
Pattern Classification (2nd Edition)
Uncomputability: the problem of induction internalized
Theoretical Computer Science - Super-recursive algorithms and hypercomputation
Justification as truth-finding efficiency: how Ockham's Razor works
Minds and Machines - Machine learning as experimental philosophy of science
All of Statistics: A Concise Course in Statistical Inference
All of Statistics: A Concise Course in Statistical Inference
Minimum description length induction, Bayesianism, and Kolmogorov complexity
IEEE Transactions on Information Theory
Hi-index | 5.23 |
The nature of empirical simplicity and its relationship to scientific truth are long-standing puzzles. In this paper, empirical simplicity is explicated in terms of empirical effects, which are defined in terms of the structure of the inference problem addressed. Problem instances are classified according to the number of empirical effects they present. Simple answers are satisfied by simple worlds. An efficient solution achieves the optimum worst-case cost over each complexity class with respect to such costs as the number of retractions or errors prior to convergence and elapsed time to convergence. It is shown that always choosing the simplest theory compatible with experience and hanging on to it while it remains the simplest is both necessary and sufficient for efficiency.