Semi-Discrete Normalizing Flows through Differentiable Tessellation
Chen, Ricky T. Q., Amos, Brandon, Nickel, Maximilian
–arXiv.org Artificial Intelligence
Mapping between discrete and continuous distributions is a difficult task and many have had to resort to heuristical approaches. We propose a tessellation-based approach that directly learns quantization boundaries in a continuous space, complete with exact likelihood evaluations. This is done through constructing normalizing flows on convex polytopes parameterized using a simple homeomorphism with an efficient log determinant Jacobian. We explore this approach in two application settings, mapping from discrete to continuous and vice versa. Firstly, a Voronoi dequantization allows automatically learning quantization boundaries in a multidimensional space. The location of boundaries and distances between regions can encode useful structural relations between the quantized discrete values. Secondly, a Voronoi mixture model has near-constant computation cost for likelihood evaluation regardless of the number of mixture components. Empirically, we show improvements over existing methods across a range of structured data modalities.
arXiv.org Artificial Intelligence
Dec-11-2022
- Country:
- North America > United States
- New York (0.04)
- District of Columbia > Washington (0.04)
- Colorado (0.04)
- Europe
- Belgium > Flanders (0.04)
- Slovenia > Central Slovenia
- Municipality of Ljubljana > Ljubljana (0.04)
- North America > United States
- Genre:
- Research Report (0.64)
- Technology: