Random Polytope Descriptors
arXiv:2009.13987
Abstract
We introduce a class of random polytopes which simultaneously generalizes several known constructions. While being fairly general, these polytopes are also computationally exceptionally benign. We indicate how these properties can be exploited for classification and clustering tasks in data analysis. Crucially, our construction lets users smoothly trade off between a tighter description of the data and faster computation.
19 pages (v3); major rewrite (new title, more stochastic geometry, less machine learning); experiments reworked from scratch; code and data available on zenodo, doi:10.5281/zenodo.22913313
References in corpus (11)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Deep Learning in Neural Networks: An Overview
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Methods for Interpreting and Understanding Deep Neural Networks
- An Overview of Multi-Task Learning in Deep Neural Networks
- Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Disentangling by Factorising
- On Evaluating Adversarial Robustness
- Recent Advances in Autoencoder-Based Representation Learning
- Are Disentangled Representations Helpful for Abstract Visual Reasoning?