AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Semi-Discrete Normalizing Flows through Differentiable Tessellation

Ricky T. Q. Chen, Brandon Amos, Maximilian Nickel

NeurIPS 2022 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Normalizing flow training and design · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use learnable Voronoi dequantization instead of Simplex dequantizationDiscrete UCI likelihood modeling · Connect4, Forests, Mushroom, Nursery, USCensus90negative log-likelihood (nats): 13.46{ $\pm$0.01} -> 12.92{ $\pm$0.07}; 16.58{ $\pm$0.01} -> 14.20{ $\pm$0.05}; 9.26{ $\pm$0.01} -> 9.06{ $\pm$0.05}; 9.Improved
Use learnable Voronoi dequantization instead of Discrete FlowDiscrete UCI likelihood modeling · PokerHandsnegative log-likelihood (nats): 19.82{ $\pm$0.03} -> 19.86{ $\pm$0.04}Hurt
Use Voronoi rather than BinaryArgmax dequantizationPermutation-invariant itemset CNF · Retailnegative log-likelihood (nats): 10.47{ $\pm$0.42} -> 9.44{ $\pm$2.34}Improved
Use Voronoi rather than BinaryArgmax dequantizationPermutation-invariant itemset CNF · Accidentsnegative log-likelihood (nats): 6.72{ $\pm$0.23} -> 7.81{ $\pm$2.84}Hurt
Increase Voronoi embedding dimension from D=2 to D=8 (ablation)Character-level language modeling · text8bits per character: 1.39{ $\pm$0.01} -> 1.36{ $\pm$0.00}Improved
Increase Voronoi embedding dimension from D=2 to D=8 (ablation)Character-level language modeling · enwik8bits per character: 1.46{ $\pm$0.01} -> 1.39{ $\pm$0.01}Improved
Use Voronoi dequantization instead of BinaryArgmaxCharacter-level language modeling · text8 and enwik8bits per character: 1.38 -> 1.36{ $\pm$0.00}; 1.42 -> 1.39{ $\pm$0.01}Mixed
Add a Voronoi disjoint mixture layer to a coupling flowContinuous UCI density modeling · POWER, GAS, MINIBOONEnegative log-likelihood (nats): -0.44{ $\pm$0.01} -> -0.52{ $\pm$0.01}; -11.75{ $\pm$0.02} -> -12.63{ $\pm$0.05}; 10.87{ $\pm$0.06} -> 10.24{ $\pm$0.14}Improved
Add a Voronoi disjoint mixture layer to a coupling flowContinuous UCI density modeling · HEPMASSnegative log-likelihood (nats): 16.78{ $\pm$0.08} -> 16.16{ $\pm$0.01}Hurt
Add a Voronoi disjoint mixture layer to a coupling flowContinuous UCI density modeling · BSDS300negative log-likelihood (nats): -155.14{ $\pm$0.04} -> -156.59{ $\pm$0.14}Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy