On the geometry of similarity search: dimensionality curse and concentration of measure
Information Processing Letters
ACM Computing Surveys (CSUR)
Estimating the Intrinsic Dimension of Data with a Fractal-Based Method
IEEE Transactions on Pattern Analysis and Machine Intelligence
A few notes on statistical learning theory
Advanced lectures on machine learning
Distance--Based Classification with Lipschitz Functions
The Journal of Machine Learning Research
Intrinsic dimensionality estimation of submanifolds in Rd
ICML '05 Proceedings of the 22nd international conference on Machine learning
What is the Dimension of Your Binary Data?
ICDM '06 Proceedings of the Sixth International Conference on Data Mining
In Search of Non-Gaussian Components of a High-Dimensional Distribution
The Journal of Machine Learning Research
The Concentration of Fractional Distances
IEEE Transactions on Knowledge and Data Engineering
Manifold denoising as preprocessing for finding natural representations of data
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Neural Network Learning: Theoretical Foundations
Neural Network Learning: Theoretical Foundations
Geodesic entropic graphs for dimension and entropy estimation in manifold learning
IEEE Transactions on Signal Processing
Curse of Dimensionality in Pivot Based Indexes
SISAP '09 Proceedings of the 2009 Second International Workshop on Similarity Search and Applications
On local intrinsic dimension estimation and its applications
IEEE Transactions on Signal Processing
Indexability, concentration, and VC theory
Proceedings of the Third International Conference on SImilarity Search and APplications
Proceedings of the Fourth International Conference on SImilarity Search and APplications
Succinct nearest neighbor search
Proceedings of the Fourth International Conference on SImilarity Search and APplications
Model order selection for boolean matrix factorization
Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining
Indexability, concentration, and VC theory
Journal of Discrete Algorithms
Polyphasic metric index: reaching the practical limits of proximity searching
SISAP'12 Proceedings of the 5th international conference on Similarity Search and Applications
Hi-index | 0.00 |
We perform a deeper analysis of an axiomatic approach to the concept of intrinsic dimension of a dataset proposed by us in the IJCNN'07 paper. The main features of our approach are that a high intrinsic dimension of a dataset reflects the presence of the curse of dimensionality (in a certain mathematically precise sense), and that dimension of a discrete i.i.d. sample of a low-dimensional manifold is, with high probability, close to that of the manifold. At the same time, the intrinsic dimension of a sample is easily corrupted by moderate high-dimensional noise (of the same amplitude as the size of the manifold) and suffers from prohibitively high computational complexity (computing it is an NP-complete problem). We outline a possible way to overcome these difficulties.