Isometric Projection
نویسندگان
چکیده
Recently the problem of dimensionality reduction has received a lot of interests in many fields of information processing. We consider the case where data is sampled from a low dimensional manifold which is embedded in high dimensional Euclidean space. The most popular manifold learning algorithms include Locally Linear Embedding, ISOMAP, and Laplacian Eigenmap. However, these algorithms are nonlinear and only provide the embedding results of training samples. In this paper, we propose a novel linear dimensionality reduction algorithm, called Isometric Projection. Isometric Projection constructs a weighted data graph where the weights are discrete approximations of the geodesic distances on the data manifold. A linear subspace is then obtained by preserving the pairwise distances. In this way, Isometric Projection can be defined everywhere. Comparing to Principal Component Analysis (PCA) which is widely used in data processing, our algorithm is more capable of discovering the intrinsic geometrical structure. Specially, PCA is optimal only when the data space is linear, while our algorithm has no such assumption and therefore can handle more complex data space. Experimental results on two real life data sets illustrate the effectiveness of the proposed method.
منابع مشابه
Contractively Complemented Subspaces of Pre-symmetric Spaces
In 1965, Ron Douglas proved that if X is a closed subspace of an L-space and X is isometric to another L-space, then X is the range of a contractive projection on the containing L-space. In 1977 Arazy-Friedman showed that if a subspace X of C1 is isometric to another C1-space (possibly finite dimensional), then there is a contractive projection of C1 onto X. In 1993 Kirchberg proved that if a s...
متن کاملA Quasi-isometric Embedding Algorithm
The Whitney embedding theorem gives an upper bound on the smallest embedding dimension of a manifold. If a data set lies on a manifold, a random projection into this reduced dimension will retain the manifold structure. Here we present an algorithm to find a projection that distorts the data as little as possible.
متن کاملEla Isometric Tight Frames
A d × n matrix, n ≥ d, whose columns have equal length and whose rows are orthonormal is constructed. This is equivalent to finding an isometric tight frame of n vectors in R d (or C d), or writing the d × d identity matrix I = d n n i=1 P i , where the P i are rank 1 orthogonal projections. The simple inductive procedure given shows that there are many such isometric tight frames.
متن کاملIsometric Projection by Deng Cai , Xiaofei He , and
Recently the problem of dimensionality reduction has received a lot of interests in many fields of information processing, including data mining, information retrieval, and pattern recognition. We consider the case where data is sampled from a low dimensional manifold which is embedded in high dimensional Euclidean space. The most popular manifold learning algorithms include Locally Linear Embe...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007