Research map / Time series / Causal and generative time series
Fully Neural Network based Model for General Temporal Point Processes
Takahiro Omi, naonori ueda, Kazuyuki Aihara
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use a flexible neural-network hazard model instead of fixed-form hazard models | RNN temporal point process · Synthetic datasets | Test negative log-likelihood | Improved |
| Use a flexible neural-network hazard model instead of fixed-form hazard models | RNN temporal point process · Real datasets | Test negative log-likelihood: greater than 0.5 | Improved |
| Use a flexible neural-network hazard model instead of the strongest baseline | RNN temporal point process · Average across time-prediction datasets | MAE: 0.766 -> 0.756 | Improved |
| Use a flexible neural-network hazard model instead of the strongest baseline | RNN temporal point process · N-Poisson | MAE: 0.704 -> 0.710 | Hurt |
| Use a flexible neural-network hazard model instead of the strongest baseline | RNN temporal point process · Finance | MAE: 0.839 -> 0.847 | Hurt |
| Use a flexible neural-network hazard model instead of the strongest baseline | RNN temporal point process · SC | MAE: 0.494 -> 0.496 | Hurt |
| Replace CT-LSTM with the proposed neural-network model | Temporal point process prediction · Average across datasets | MNLL difference vs CT-LSTM: 0.064 | Improved |
| Replace CT-LSTM with the proposed neural-network model | Temporal point process prediction · Average across datasets | MAE difference vs CT-LSTM: 0.009 | Improved |
Closest papers by meaning
- Modeling the Intensity Function of Point Process Via Recurrent Neural Networks (AAAI 2017 · similarity 0.94)
- On Non-asymptotic Theory of Recurrent Neural Networks in Temporal Point Processes (JMLR 2025 · similarity 0.90)
- Neural Jump-Diffusion Temporal Point Processes (ICML 2024 · similarity 0.86)
- Interacting Diffusion Processes for Event Sequence Forecasting (ICML 2024 · similarity 0.85)
- EasyTPP: Towards Open Benchmarking Temporal Point Processes (ICLR 2024 · similarity 0.85)
- Exact, Fast and Expressive Poisson Point Processes via Squared Neural Families (AAAI 2024 · similarity 0.84)
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.
