On the Estimation of Pointwise Dimension
Our goal in this paper is to develop an effective estimator of fractal dimension. We survey existing ideas in dimension estimation, with a focus on the currently popular method of Grassberger and Procaccia for the estimation of correlation dimension. There are two major difficulties in estimation based on this method. The first is the insensitivity of correlation dimension itself to differences in dimensionality over data, which we term "dimension blindness". The second comes from the reliance of the method on the inference of limiting behavior from finite data. We propose pointwise dimension as an object for estimation in response to the dimension blindness of correlation dimension. Pointwise dimension is a local quantity, and the distribution of pointwise dimensions over the data contains the information to which correlation dimension is blind. We use a "limit-free" description of pointwise dimension to develop a new estimator. We conclude by discussing potential applications of our estimator as well as some challenges it raises.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
X-HRNet: Towards Lightweight Human Pose Estimation with Spatially Unidimensional Self-Attention
High-resolution representation is necessary for human pose estimation to achieve high performance, and the ensuing problem is high computational complexity. In particular, predominant pose estimation methods estimate hum…
Pose EstimationSome pointwise and decidable properties of non-uniform cellular automata
For non-uniform cellular automata (NUCA) with finite memory over an arbitrary universe with multiple local transition rules, we show that pointwise nilpotency, pointwise periodicity, and pointwise eventual periodicity pr…
Clustering by latent dimensions
This paper introduces a new clustering technique, called {\em dimensional clustering}, which clusters each data point by its latent {\em pointwise dimension}, which is a measure of the dimensionality of the data set loca…
ClusteringDenoising distances beyond the volumetric barrier
We study the problem of reconstructing the latent geometry of a $d$-dimensional Riemannian manifold from a random geometric graph. While recent works have made significant progress in manifold recovery from random geomet…
Mollified Value Learning
Offline goal-conditioned reinforcement learning (GCRL) learns goal-reaching behaviors from static datasets, but accurate value estimation remains challenging under limited state-action coverage. Existing physics-informed…
Representation LearningReinforcement Learning