AI Paper Atlas

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

Boosted Generative Models

Aditya Grover, Stefano Ermon

AAAI 2018 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Score-based generative modeling analysis · 41 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
Replace additive boosting with multiplicative discriminative boostingMixture-of-two-Gaussians base model · Mixture of Gaussians test setNLL (nats): 4.69 ± 0.01 -> 4.35 ± 0.01Improved
Use negative cross-entropy instead of Hellinger distance for the discriminator (ablation)DiscBGM · Mixture of Gaussians test setNLL (nats): 4.35 ± 0.01 -> 4.42 ± 0.01Hurt
Use additive rather than multiplicative boosting (ablation)Generative boosting · Mixture of Gaussians test setNLL (nats): 4.58 ± 0.10 -> 4.64 ± 0.02Hurt
Add discriminative multiplicative boostingMixture of Bernoullis · Density estimation across benchmark datasetsNLL (nats): 42.23 -> 34.51; 11.27 -> 10.91; 55.67 -> 34.93; 99.42 -> 98.45; 11.72 -> 11.13; 63.13 -> 54.79Improved
Add discriminative multiplicative boostingSum-Product Network · Density estimation across benchmark datasetsNLL (nats): 31.08 -> 28.09; 14.94 -> 10.88; 26.70 -> 23.69; 92.60 -> 86.63; 12.71 -> 10.67; 19.19 -> 17.82Improved
Add discriminative multiplicative boostingMixture of Bernoullis · Classification across benchmark datasetsprediction accuracy: 0.8395 -> 0.9043; 0.9776 -> 0.9792; 0.8461 -> 0.9267; 0.7517 -> 0.7526; 0.9817 -> 0.9831; 0.9922 -> 0.9927Improved
Add discriminative multiplicative boostingSum-Product Network · Classification across benchmark datasetsprediction accuracy: 0.9258 -> 0.9416; 0.9780 -> 0.9791; 0.9599 -> 0.9636; 0.7799 -> 0.7811; 0.9824 -> 0.9838; 0.9982 -> 0.9982Mixed
Use additive boosting rather than the base model (ablation)Mixture of Bernoullis · Density estimation across benchmark datasetsNLL (nats): 42.23 -> 43.19; 11.27 -> 12.24; 55.67 -> 55.91; 99.42 -> 100.37; 11.72 -> 12.57; 63.13 -> 63.73Hurt
Replace the base model with GenBGM (ablation)Mixture of Bernoullis · Density estimation across benchmark datasetsNLL (nats): 42.23 -> 41.43; 11.27 -> 11.20; 55.67 -> 50.66; 99.42 -> 99.23; 11.72 -> 12.41; 63.13 -> 63.19Mixed
Use the uniform model-weighting heuristic (ablation)DiscBGM · Mixture of GaussiansNLL (nats)Hurt
Use the unity model-weighting heuristic (ablation)GenBGM · Mixture of GaussiansNLL (nats)Hurt
Use the decay model-weighting heuristic (ablation)GenBGM and DiscBGM · Mixture of GaussiansNLL (nats)Improved

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