Ming Li

Ming Li

Auto-generated profile, based on publicly available information

Ming Li

Dept of Computer Science University of California 93106 Santa Barbara CA USA

Research Focus & Metrics

Academic Career Length

27Years (2000-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2002 in Journal of Computer and System Sciences
Verified
Journal Article
Closed access
MLMing Li
Ming Li
BMBin Ma
Bin Ma
LWLusheng Wang
Lusheng Wang

8 February 2002 in Random Structures & Algorithms
Verified
Journal Article
Closed access
PDF file
TJTao Jiang
Tao Jiang
MLMing Li
Ming Li
PVPaul Vitányi
Paul Vitányi

1 September 2000 in Journal of Computer Science and Technology
Verified
Journal Article
Closed access
PDF file
TJTao Jiang
Tao Jiang
MLMing Li
Ming Li
PVPaul Vitányi
Paul Vitányi

23 April 2003 in Computer Methods and Programs in Biomedicine
Verified
Journal Article
Closed access
HSHuandong Sun
Huandong Sun
MLMing Li
Ming Li
YXYing Xu
Ying Xu

23 May 2000 in arXiv
Verified
Preprint
Open access
PDF file
QGQiong Gao
Qiong Gao
MLMing Li
Ming Li
PVPaul Vitányi
Paul Vitányi
The Minimum Description Length (MDL) principle is solidly based on a provably ideal method of inference using Kolmogorov complexity. We test how the theory behaves in practice on a general problem in model selection: that of learning the best model granularity. The performance of a model depends critically on the granularity, for example the choice of precision of the parameters. Too high precision generally involves modeling of accidental noise and too low precision may lead to confusion of models that should be distinguished. This precision is often determined ad hoc. In MDL the best model is the one that most compresses a two-part code of the data set: this embodies ``Occam's Razor.'' In two quite different experimental settings the theoretical value determined using MDL coincides with the best value found experimentally. In the first experiment the task is to recognize isolated handwritten characters in one subject's handwriting, irrespective of size and orientation. Based on a new modification of elastic matching, using multiple prototypes per character, the optimal prediction rate is predicted for the learned parameter (length of sampling interval) considered most likely by MDL, which is shown to coincide with the best value found experimentally. In the second experiment the task is to model a robot arm with two degrees of freedom using a three layer feed-forward neural network where we need to determine the number of nodes in the hidden layer giving best modeling performance. The optimal model (the one that extrapolizes best on unseen examples) is predicted for the number of nodes in the hidden layer considered most likely by MDL, which again is found to coincide with the best value found experimentally.

10 November 2003 in arXiv
Verified
Preprint
Open access
PDF file
TJTao Jiang
Tao Jiang
MLMing Li
Ming Li
PVPaul Vitányi
Paul Vitányi
From among $ {n \choose 3}$ triangles with vertices chosen from $n$ points in the unit square, let $T$ be the one with the smallest area, and let $A$ be the area of $T$. Heilbronn's triangle problem asks for the maximum value assumed by $A$ over all choices of $n$ points. We consider the average-case: If the $n$ points are chosen independently and at random (with a uniform distribution), then there exist positive constants $c$ and $C$ such that $c/n^3 < \mu_n < C/n^3$ for all large enough values of $n$, where $\mu_n$ is the expectation of $A$. Moreover, $c/n^3 < A < C/n^3$, with probability close to one. Our proof uses the incompressibility method based on Kolmogorov complexity; it actually determines the area of the smallest triangle for an arrangement in ``general position.''