Research map / Probabilistic and scientific modeling / Variational and generative sampling
Noise-Contrastive Estimation for Multivariate Point Processes
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 changed | Where | Measured | Effect |
|---|---|---|---|
| use ranking NCE instead of MLE for training | Neural Hawkes Process · synthetic datasets, K=10000 | intensity evaluations and wall-clock time to reach competitive held-out log-like | Helped |
| use proposed NCE instead of binary NCE (b-NCE) and LSE | Neural Hawkes Process · EuroEmail, BitcoinOTC | held-out log-likelihood / speed | Helped |
| always redraw noise samples instead of reusing them (ablation) | NCE · synthetic datasets | generalization and training speed | Mixed |
| use neural noise distribution q instead of Poisson q (ablation) | NCE · EuroEmail, BitcoinOTC | held-out log-likelihood | Helped |
| pretrain noise distribution q on data versus leaving it untrained (ablation) | NCE · social interaction datasets | generalization, convergence, variance | Helped |
| use C=5 coarse types instead of C=1 in noise model (ablation) | NCE · RoboCup | held-out log-likelihood | Helped |
| use NCE with M=1 instead of M=5 or 10 (ablation) | NCE · RoboCup | final log-likelihood | Hurt |
Closest papers by meaning
- Hierarchical Contrastive Learning for Temporal Point Processes (AAAI 2023 · similarity 0.90)
- Information Theoretic Learning for Diffusion Models with Warm Start (NeurIPS 2025 · similarity 0.85)
- Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models (ICLR 2024 · similarity 0.85)
- Dimension-free Score Matching and Time Bootstrapping for Diffusion Models (NeurIPS 2025 · similarity 0.85)
- Unlocking Point Processes through Point Set Diffusion (ICLR 2025 · similarity 0.85)
- Diffusion Models With Learned Adaptive Noise (NeurIPS 2024 · similarity 0.85)
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.