Overview
This editorial highlights the upcoming workshop on Learning with Temporal Point Processes, scheduled to take place at NeurIPS 2019. This event aims to foster understanding and application of temporal point processes within the machine learning community, emphasizing their significance in various domains.
Background & Relevance
Temporal point processes have gained traction in recent years due to their effectiveness in modeling and predicting events in social and information systems. These processes are crucial for developing human-centered machine learning models that consider the asynchronous nature of human decision-making. By integrating temporal point processes into machine learning, researchers can enhance predictive capabilities and improve algorithmic performance.
Key Details
- Submission Deadline: September 15, 23:59 AOE
- Author Notification: September 30
- Submission Format: Extended abstracts (maximum 4 pages, excluding references)
- Submission Link: EasyChair Submission
- Proceedings: No formal proceedings; accepted abstracts may link to arXiv or be published as PDFs on the workshop webpage.
Eligibility & Participation
The workshop is open to researchers and practitioners interested in the applications and methodologies of temporal point processes in machine learning. It targets a diverse audience, including those from various interdisciplinary backgrounds.
Submission or Application Guidelines
To participate, authors should prepare extended abstracts that adhere to the NeurIPS formatting guidelines. Submissions must be anonymized and can include work that is either recently published or currently under review. Authors are encouraged to submit their abstracts through the provided EasyChair link.
Additional Context / Real-World Relevance
Understanding temporal point processes is vital for advancing machine learning applications, especially in fields like social network analysis, healthcare, and economics. By addressing the interplay between algorithmic decisions and human behavior, this workshop will contribute to the development of more robust and effective machine learning systems.
Conclusion
The workshop on Learning with Temporal Point Processes at NeurIPS 2019 presents a valuable opportunity for researchers to engage with cutting-edge methodologies and applications. Interested participants are encouraged to submit their work and contribute to this important discourse in the AI/ML community.
Category: Conferences & Workshops
Tags: temporal point processes, machine learning, neural networks, reinforcement learning, predictive models, causal learning, deep learning, generative models
