Part of Advances in Neural Information Processing Systems 16 (NIPS 2003)
Denis Chigirev, William Bialek
We introduce an information theoretic method for nonparametric, non- linear dimensionality reduction, based on the inﬁnite cluster limit of rate distortion theory. By constraining the information available to manifold coordinates, a natural probabilistic map emerges that assigns original data to corresponding points on a lower dimensional manifold. With only the information-distortion trade off as a parameter, our method de- termines the shape of the manifold, its dimensionality, the probabilistic map and the prior that provide optimal description of the data.
1 A simple example
Some data sets may not be as complicated as they appear. Consider the set of points on a plane in Figure 1. As a two dimensional set, it requires a two dimensional density ρ(x, y) for its description. Since the data are sparse the density will be almost singular. We may use a smoothing kernel, but then the data set will be described by a complicated combina- tion of troughs and peaks with no obvious pattern and hence no ability to generalize. We intuitively, however, see a strong one dimensional structure (a curve) underlying the data. In this paper we attempt to capture this intuition formally, through the use of the inﬁnite cluster limit of rate distortion theory.
Any set of points can be embedded in a hypersurface of any intrinsic dimensionality if we allow that hypersurface to be highly “folded.” For example, in Figure 1, any curve that goes through all the points gives a one dimensional representation. We would like to avoid such solutions, since they do not help us discover structure in the data. Looking for a simpler description one may choose to penalize the curvature term . The problem with this approach is that it is not easily generalized to multiple dimensions, and requires the dimensionality of the solution as an input.
An alternative approach is to allow curves of all shapes and sizes, but to send the reduced coordinates through an information bottleneck. With a ﬁxed number of bits, position along a highly convoluted curve becomes uncertain. This will penalize curves that follow the data too closely (see Figure 1). There are several advantages to this approach. First, it removes the artiﬁciality introduced by Hastie  of adding to the cost function only orthogonal er- rors. If we believe that data points fall out of the manifold due to noise, there is no reason to treat the projection onto the manifold as exact. Second, it does not require the dimension-
Figure 1: Rate distortion curve for a data set of 25 points (red). We used 1000 points to represent the curve which where initialized by scattering them uni- formly on the plane. Note that the pro- duced curve is well deﬁned, one dimen- sional and smooth.
ality of the solution manifold as an input. By adding extra dimensions, one quickly looses the precision with which manifold points are speciﬁed (due to the ﬁxed information bottle- neck). Hence, the optimal dimension emerges naturally. This also means that the method works well in many dimensions with no adjustments. Third, the method handles sparse data well. This is important since in high dimensional spaces all data sets are sparse, i.e. they look like points in Figure 1, and the density estimation becomes impossible. Luckily, if the data are truly generated by a lower dimensional process, then density estimation in the data space is not important (from the viewpoint of prediction or any other). What is critical is the density of the data along the manifold (known in latent variable modeling as a prior), and our algorithm ﬁnds it naturally.
2 Latent variable models and dimensionality reduction
Recently, the problem of reducing the dimensionality of a data set has received renewed attention [3,4]. The underlying idea, due to Hotelling , is that most of the variation in many high dimensional data sets can often be explained by a few latent variables. Alterna- tively, we say that rather than ﬁlling the whole space, the data lie on a lower dimensional manifold. The dimensionality of this manifold is the dimensionality of the latent space and the coordinate system on this manifold provides the latent variables.
Traditional tools of principal component analysis (PCA) and factor analysis (FA) are still the most widely used methods in data analysis. They project the data onto a hyperplane, so the reduced coordinates are easy to interpret. However, these methods are unable to deal with nonlinear correlations in a data set. To accommodate nonlinearity in a data set, one has to relax the assumption that the data is modeled by a hyperplane, and allow a general low dimensional manifold of unknown shape and dimensionality. The same questions that we asked in the previous section apply here. What do we mean by requiring that “the manifold models the data well”? In the next section, we formalize this notion by deﬁning the manifold description of data as a doublet (the shape of the manifold and the projection map). Note that we do not require the probability distribution over the manifold (known for generative models [6,7] as a prior distribution over the latent variables and postulated a priori). It is completely determined by the doublet.
Nonlinear correlations in data can also be accommodated implicitly, without constructing an actual low dimensional manifold. By mapping the data from the original space to an even higher dimensional feature space, we may hope that the correlations will become linearized and PCA will apply. Kernel methods  allow us to do this without actually constructing an explicit map to feature space. They introduce nonlinearity through an a priori nonlinear kernel. Alternatively, autoassociative neural networks  force the data through a bottleneck (with an internal layer of desired dimensionality) to produce a reduced
024681012123456789 description. One of the disadvantages of these methods is that the results are not easy to interpret.
Recent attempts to describe a data set with a low dimensional representation generally fol- low into two categories: spectral methods and density modeling methods. Spectral methods (LLE , ISOMAP , Laplacian eigenmaps ) give reduced coordinates of an a pri- ori dimensionality by introducing a quadratic cost function in reduced coordinates (hence eigenvectors are solutions) that mimics the relationships between points in the original data space (geodesic distance for ISOMAP, linear reconstruction for LLE). Density modeling methods (GTM , GMM ) are generative models that try to reproduce the data with fewer variables. They require a prior and a parametric generative model to be introduced a priori and then ﬁnd optimal parameters via maximum likelihood.
The approach that we will take is inspired by the work of Kramer  and others who tried to formulate dimensionality reduction as a compression problem. They tried to solve the problem by building an explicit neural network encoder-decoder system which restricted the information implicitly by limiting the number of nodes in the bottleneck layer. Extend- ing their intuition with the tools of information theory, we recast dimensionality reduction as a compression problem where the bottleneck is the information available to manifold coordinates. This allows us to deﬁne the optimal manifold description as that which pro- duces the best reconstruction of the original data set, given that the coordinates can only be transmitted through a channel of ﬁxed capacity.
3 Dimensionality reduction as compression
Suppose that we have a data set X in a high dimensional state space RD described by a density function ρ(x). We would like to ﬁnd a “simpliﬁed” description of this data set. One may do so by visualizing a lower dimensional manifold M that “almost” describes the data. If we have a manifold M and a stochastic map PM : x → PM(µ|x) to points µ on the manifold, we will say that they provide a manifold description of the data set X. Note that the stochastic map here is well justiﬁed: if a data point does not lie exactly on the manifold then we should expect some uncertainty in the estimation of the value of its latent variables. Also note that we do not need to specify the inverse (generative) map: M → RD; it can be obtained by Bayes’ rule. The manifold description (M, PM) is a less than faithful representation of the data. To formalize this notion we will introduce the distortion measure D(M, PM, ρ):