AI Paper Atlas

Research map / Time series / Causal and generative time series

Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes

YIXUAN ZHANG, Quyu Kong, Feng Zhou

NeurIPS 2023 · Time series › Causal and generative time series · approach: Generative temporal point processes · 2 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 deep kernel DMPP with deep-kernel DKMPP trained by score matching (RQ kernel) (ablation)DMPP · Crimes in VancouverACC (%): 51.52 -> 80.16Improved
add multimodal covariates and score-based estimator versus DeepSTPPDeepSTPP · NYC Vehicle CollisionsTLL: 396.60 -> 411.03Improved
compare against HomoPoissonScore-DKMPP (RQ) · NYC Vehicle CollisionsACC (%): 66.811 -> 79.42Improved
use Score-DKMPP+ (denoising) instead of Score-DKMPP with OU kernel (ablation)Score-DKMPP · NYC Complaint DataTLL: 3.06 -> 4.28Improved
use Score-DKMPP+ (RBF) instead of Score-DKMPP (RBF) (ablation)Score-DKMPP · NYC Vehicle CollisionsTLL: 409.02 -> 402.54Hurt
increase representative points from 64 to 125 (ablation)Score-DKMPP · syntheticRMSE: 3.86 -> 3.66Improved
increase representative points from 125 to 216 (ablation)Score-DKMPP · syntheticRMSE: 3.66 -> 3.66No clear effect
increase layers from 1 to 4 (ablation)Score-DKMPP · syntheticRMSE: 3.84 -> 4.13Hurt
increase layers from 1 to 4 (ablation)Score-DKMPP+ · syntheticRMSE: 3.78 -> 4.08Hurt
batch size 100 versus 200 (ablation)Score-DKMPP · syntheticRMSE: 4.07 -> 3.47Improved
batch size 50 versus 100 (ablation)Score-DKMPP+ · syntheticRMSE: 3.67 -> 3.61No clear effect
increase noise variance from 0.01 to 10 (ablation)Score-DKMPP+ · syntheticintensity recoveryHurt

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