Research map / Bandits and online learning / Online convex optimization and games
Online Learning for Multivariate Hawkes 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 |
|---|---|---|---|
| Decrease discretization level delta from 0.5 to 0.05 (and to 0.01) (ablation) | NPOLE-MHP · Synthetic 5-dim MHP, T=10^4 | average L1 error: 4.80 -> 1.86 (delta 0.5 -> 0.05) | Helped |
| Increase regularization coefficient zeta from 1e-8 to 1e-2 (ablation) | NPOLE-MHP · Synthetic 5-dim MHP, T=10^4 | average L1 error: 1.86 -> 4.64 at log10 zeta=0 (delta 0.05 row: 3.10 at -2) | Hurt |
| Online NPOLE-MHP vs batch MLE estimators on synthetic data | NPOLE-MHP · Synthetic 5-dim MHP | run time and goodness-of-fit | No clear effect |
| Online RKHS learning vs parametric online DMD/OGD on synthetic data | NPOLE-MHP · Synthetic 5-dim MHP | visual fit of triggering functions | Helped |
| Online RKHS learning vs DMD and OGD on memetracker data | NPOLE-MHP · Memetracker 20 dimensions | cumulative loss | Helped |
| Online NPOLE-MHP vs OGD/DMD on test generalization (100 dims) | NPOLE-MHP · Memetracker 100 dimensions, 2x10^5 events | average loss per iteration on test data: 0.01 vs 0.14 test loss for OGD/DMD | Helped |
| Scale dimension and horizon for NPOLE-MHP (computation time) | NPOLE-MHP · Memetracker, p from 20 to 100 | average CPU-time per triggering function | No clear effect |
Closest papers by meaning
- Multivariate Hawkes Processes for Large-Scale Inference (AAAI 2017 · similarity 0.88)
- A Representer Theorem for Hawkes Processes via Penalized Least Squares Minimization (ICLR 2026 · similarity 0.88)
- Learning Hawkes Processes from a handful of events (NeurIPS 2019 · similarity 0.87)
- Learning Hawkes Processes Under Synchronization Noise (ICML 2019 · similarity 0.87)
- Variational Inference for Sparse Gaussian Process Modulated Hawkes Process (AAAI 2020 · similarity 0.87)
- Cumulants of Hawkes Processes are Robust to Observation Noise (ICML 2021 · similarity 0.87)
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.