AI Paper Atlas

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

Poisson Random Fields for Dynamic Feature Models

Valerio Perrone, Paul A. Jenkins, Dario Spanò, Yee Whye Teh

JMLR 2017 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 50 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
Model time with the dynamic WF-IBP topic model instead of a static topic model (ablation)fixed-K topic model · Synthetic topic data (9 time points, 30 documents each)Frobenius norm of difference with true Z_t: 1.78 -> 3.63 at t1 (dynamic lower at every time, e.g. 0.72 vs 2.84 at t3)Improved
Model time with the dynamic topic model instead of static, on held-out words (ablation)fixed-K topic model · Synthetic topic data, held-out word perplexitytest-set perplexityImproved
Model time with the dynamic topic model instead of static on NIPS 1999 held-out words (50-80%) (ablation)fixed-K topic model · NIPS papers (train 1987-1998, test 1999)test-set perplexityImproved
Increase observed documents per time point from 10 to 20, 40, 60WF-IBP topic model · Synthetic topic data (100 documents, 2 time points)reconstruction of top-10 word probabilitiesImproved

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