Deep Reinforcement Learning of Marked Temporal Point Processes

Upadhyay, Utkarsh; De, Abir; Gomez-Rodriguez, Manuel

doi:10.48550/arxiv.1805.09360

Cited by 4 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of directly summing over all past events, as in models based on the Hawkes process (Hawkes, 1971), a fixed length vector representation of the past is learnt and updated at each new time step. Forecasts can then be made by modelling the conditional intensity function on this vector (Xiao et al, 2017;Li et al, 2018;Upadhyay et al, 2018;Huang et al, 2019;Omi et al, 2019), or instead through directly modelling the probability of the next event (Shchur et al, 2019). We direct the reader to Shchur et al (2021) for a review of neural point process models.…”

Section: Introductionmentioning

confidence: 99%

Forecasting the 2016-2017 Central Apennines Earthquake Sequence with a Neural Point Process

Stockman¹,

Lawson²,

Werner³

2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Forecasting the 2016-2017 Central Apennines Earthquake Sequence with a Neural Point Process

Stockman¹,

Lawson²,

Werner³

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A classic approach to model event sequences as TPPs is through the Hawkes process, in which a simple parametric form is used to capture temporal dependence among events (Hawkes 1971). In the past few years, many researchers have developed neural TPP models that have achieved fruitful results on standard benchmarks for predictive tasks, because neural networks are ca-pable of capturing more complex dependencies (Du et al 2016;Mei and Eisner 2016;Xiao et al 2017;Upadhyay, De, and Gomez-Rodriguez 2018;Omi, Ueda, and Aihara 2019;Shchur, Biloš, and Günnemann 2019;Zuo et al 2020;Zhang et al 2020a;Shchur et al 2020;Boyd et al 2020;Gao et al 2020;Gu 2021).…”

Section: Introductionmentioning

confidence: 99%

Concurrent Multi-Label Prediction in Event Streams

Shou

Gao²,

Subramanian³

et al. 2023

AAAI

View full text Add to dashboard Cite

Streams of irregularly occurring events are commonly modeled as a marked temporal point process. Many real-world datasets such as e-commerce transactions and electronic health records often involve events where multiple event types co-occur, e.g. multiple items purchased or multiple diseases diagnosed simultaneously. In this paper, we tackle multi-label prediction in such a problem setting, and propose a novel Transformer-based Conditional Mixture of Bernoulli Network (TCMBN) that leverages neural density estimation to capture complex temporal dependence as well as probabilistic dependence between concurrent event types. We also propose potentially incorporating domain knowledge in the objective by regularizing the predicted probability. To represent probabilistic dependence of concurrent event types graphically, we design a two-step approach that first learns the mixture of Bernoulli network and then solves a least-squares semi-definite constrained program to numerically approximate the sparse precision matrix from a learned covariance matrix. This approach proves to be effective for event prediction while also providing an interpretable and possibly non-stationary structure for insights into event co-occurrence. We demonstrate the superior performance of our approach compared to existing baselines on multiple synthetic and real benchmarks.

show abstract

“…Instead of directly summing over all past events, as in models based on the Hawkes process (Hawkes, 1971), a fixed length vector representation of the past is learned and updated at each new time step. Forecasts can then be made by modeling the conditional intensity function on this vector (Huang et al, 2019;Li et al, 2018;Omi et al, 2019;Upadhyay et al, 2018;Xiao et al, 2017), or instead through directly modeling the probability of the next event (Shchur et al, 2019). We direct the reader to Shchur et al (2021) for a review of neural point process models.…”

mentioning

confidence: 99%

Forecasting the 2016–2017 Central Apennines Earthquake Sequence With a Neural Point Process

Stockman,

Lawson,

Werner

2023

Earth's Future

View full text Add to dashboard Cite

Point processes have been dominant in modeling the evolution of seismicity for decades, with the epidemic‐type aftershock sequence (ETAS) model being most popular. Recent advances in machine learning have constructed highly flexible point process models using neural networks to improve upon existing parametric models. We investigate whether these flexible point process models can be applied to short‐term seismicity forecasting by extending an existing temporal neural model to the magnitude domain and we show how this model can forecast earthquakes above a target magnitude threshold. We first demonstrate that the neural model can fit synthetic ETAS data, however, requiring less computational time because it is not dependent on the full history of the sequence. By artificially emulating short‐term aftershock incompleteness in the synthetic data set, we find that the neural model outperforms ETAS. Using a new enhanced catalog from the 2016–2017 Central Apennines earthquake sequence, we investigate the predictive skill of ETAS and the neural model with respect to the lowest input magnitude. Constructing multiple forecasting experiments using the Visso, Norcia and Campotosto earthquakes to partition training and testing data, we target M3+ events. We find both models perform similarly at previously explored thresholds (e.g., above M3), but lowering the threshold to M1.2 reduces the performance of ETAS unlike the neural model. We argue that some of these gains are due to the neural model's ability to handle incomplete data. The robustness to missing data and speed to train the neural model present it as an encouraging competitor in earthquake forecasting.

show abstract

Deep Reinforcement Learning of Marked Temporal Point Processes

Cited by 4 publications

References 19 publications

Forecasting the 2016-2017 Central Apennines Earthquake Sequence with a Neural Point Process

Forecasting the 2016-2017 Central Apennines Earthquake Sequence with a Neural Point Process

Concurrent Multi-Label Prediction in Event Streams

Forecasting the 2016–2017 Central Apennines Earthquake Sequence With a Neural Point Process

Contact Info

Product

Resources

About