DeepAI AI Chat
Log In Sign Up

Bundle Networks: Fiber Bundles, Local Trivializations, and a Generative Approach to Exploring Many-to-one Maps

by   Nico Courts, et al.

Many-to-one maps are ubiquitous in machine learning, from the image recognition model that assigns a multitude of distinct images to the concept of "cat" to the time series forecasting model which assigns a range of distinct time-series to a single scalar regression value. While the primary use of such models is naturally to associate correct output to each input, in many problems it is also useful to be able to explore, understand, and sample from a model's fibers, which are the set of input values x such that f(x) = y, for fixed y in the output space. In this paper we show that popular generative architectures are ill-suited to such tasks. Motivated by this we introduce a novel generative architecture, a Bundle Network, based on the concept of a fiber bundle from (differential) topology. BundleNets exploit the idea of a local trivialization wherein a space can be locally decomposed into a product space that cleanly encodes the many-to-one nature of the map. By enforcing this decomposition in BundleNets and by utilizing state-of-the-art invertible components, investigating a network's fibers becomes natural.


page 8

page 16


Machine Learning of Time Series Using Time-delay Embedding and Precision Annealing

Tasking machine learning to predict segments of a time series requires e...

Time Series Regression

This paper introduces Time Series Regression (TSR): a little-studied tas...

Generalisation in fully-connected neural networks for time series forecasting

In this paper we study the generalisation capabilities of fully-connecte...

DANLIP: Deep Autoregressive Networks for Locally Interpretable Probabilistic Forecasting

Despite the high performance of neural network-based time series forecas...

Deep Probabilistic Time Series Forecasting using Augmented Recurrent Input for Dynamic Systems

The demand of probabilistic time series forecasting has been recently ra...

Structural time series grammar over variable blocks

A structural time series model additively decomposes into generative, se...

Fiber Bundle Morphisms as a Framework for Modeling Many-to-Many Maps

While it is not generally reflected in the `nice' datasets used for benc...