Relaxing Bijectivity Constraints with Continuously Indexed Normalising Flows
We show that normalising flows become pathological when used to model targets whose supports have complicated topologies. In this scenario, we prove that a flow must become arbitrarily numerically noninvertible in order to approximate the target closely. This result has implications for all flow-based models, and especially Residual Flows (ResFlows), which explicitly control the Lipschitz constant of the bijection used. To address this, we propose Continuously Indexed Flows (CIFs), which replace the single bijection used by normalising flows with a continuously indexed family of bijections, and which can intuitively "clean up" mass that would otherwise be misplaced by a single bijection. We show theoretically that CIFs are not subject to the same topological limitations as normalising flows, and obtain better empirical performance on a variety of models and benchmarks.
Code (3)
Tasks
Density EstimationNormalising FlowsSimilar Papers 제목 키워드 기반
MixerFlow: MLP-Mixer meets Normalising Flows
Normalising flows are generative models that transform a complex density into a simpler density through the use of bijective transformations enabling both density estimation and data generation from a single model. %Howe…
Density EstimationKolmogorov-Arnold NetworksNormalising FlowsContinuously Indexed Domain Adaptation
Existing domain adaptation focuses on transferring knowledge between domains with categorical indices (e.g., between datasets A and B). However, many tasks involve continuously indexed domains. For example, in medical ap…
Continuously Indexed Domain AdaptationDomain Adaptation$\mathtt{emuflow}$: Normalising Flows for Joint Cosmological Analysis
Given the growth in the variety and precision of astronomical datasets of interest for cosmology, the best cosmological constraints are invariably obtained by combining data from different experiments. At the likelihood …
Normalising FlowsContinuously Index Domain Adaptation
Existing domain adaptation focuses on transferring knowledge between domains with categorical indices (e.g., between datasets A and B). However, many tasks involve continuously indexed domains. For example, in medical ap…
Continuously Indexed Domain AdaptationDomain AdaptationKernelised Normalising Flows
Normalising Flows are non-parametric statistical models characterised by their dual capabilities of density estimation and generation. This duality requires an inherently invertible architecture. However, the requirement…
Density EstimationNormalising Flows