Random projections of random manifolds
نویسندگان
چکیده
Interesting data often concentrate on low dimensional smooth manifolds inside a high dimensional ambient space. Random projections are a simple, powerful tool for dimensionality reduction of such data. Previous works have studied bounds on how many projections are needed to accurately preserve the geometry of these manifolds, given their intrinsic dimensionality, volume and curvature. However, such works employ definitions of volume and curvature that are inherently difficult to compute. Therefore such theory cannot be easily tested against numerical simulations to understand the tightness of the proven bounds. We instead study typical distortions arising in random projections of an ensemble of smooth Gaussian random manifolds. We find explicitly computable, approximate theoretical bounds on the number of projections required to accurately preserve the geometry of these manifolds. Our bounds, while approximate, can only be violated with a probability that is exponentially small in the ambient dimension, and therefore they hold with high probability in cases of practical interest. Moreover, unlike previous work, we test our theoretical bounds against numerical experiments on the actual geometric distortions that typically occur for random projections of random smooth manifolds. We find our bounds are tighter than previous results by several orders of magnitude.
منابع مشابه
Learning the structure of manifolds using random projections
We present a simple variant of the k-d tree which automatically adapts to intrinsic low dimensional structure in data.
متن کاملEfficient clustering on Riemannian manifolds: A kernelised random projection approach
Reformulating computer vision problems over Riemannian manifolds has demonstrated superior performance in various computer vision applications. This is because visual data often forms a special structure lying on a lower dimensional space embedded in a higher dimensional space. However, since these manifolds belong to non-Euclidean topological spaces, exploiting their structures is computationa...
متن کاملManifold-based Approaches for Improved Classification
While manifold structure is often exploited for dimensionality reduction or feature extraction, this structure is rarely used by classification algorithms. We present a class of algorithms that utilize the low-dimensional manifold nature of signal ensembles and result in improved classification performance. The algorithms are built within theoretical frameworks that take into consideration prio...
متن کاملRandom Projections for Anchor-based Topic Inference
Recent spectral topic discovery methods are extremely fast at processing large document corpora, but scale poorly with the size of the input vocabulary. Random projections are vital to ensure speed and limit memory usage. We empirically evaluate several methods for generating random projections and measure the effect of parameters such as sparsity and dimensionality. We find that methods with s...
متن کاملInvariant manifolds for random and stochastic partial differential equations
Random invariant manifolds are geometric objects useful for understanding complex dynamics under stochastic influences. Under a nonuniform hyperbolicity or a nonuniform exponential dichotomy condition, the existence of random pseudostable and pseudo-unstable manifolds for a class of random partial differential equations and stochastic partial differential equations is shown. Unlike the invarian...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1607.04331 شماره
صفحات -
تاریخ انتشار 2016