Time series data is ubiquitous. In domains as diverse as finance, entertainment, transportation and health-care, there has been a fundamental shift away from parsimonious, infrequent measurement to nearly continuous monitoring and recording. Rapid advances in many sensing technologies, ranging from remote sensors to wearables and social sensing, are have generated a rapid growth in the size and complexity of time series archives. Thus, while time series analysis has been studied extensively in the past, its importance only continues to grow. Furthermore, modern time series data pose significant new challenges in terms of structure (e.g., irregular sampling in hospital records and spatiotemporal structure in climate data) and size (e.g. computation and storage). These challenges are compounded by the fact that the standard i.i.d. assumptions used in other areas of machine learning are often not appropriate for time series. Instead, new theory, models and algorithms are needed to process and analyze this data.
The goal of this workshop is to bring together both theoretical and applied researchers interested in the analysis of time series and the development of new algorithms to process sequential data. This includes researchers designing algorithms for specific tasks including time series prediction, classification, clustering, anomaly and change point detection, correlation discovery, dimensionality reduction as well as researchers who work on developing a general theory for learning and understanding stochastic processes. We also invite researchers from related areas, including but not limited to batch and online learning, reinforcement learning, data analysis and statistics, and econometrics, to contribute to this workshop.
|9:20 - 9:50||Opening Remarks: Vitaly Kuznetsov|
|9:50 - 10:35||Invited Talk: Rob Hyndman|
|10:35 - 11:00||Morning Coffee Break|
|11:00 - 12:00||Poster Session|
|12:00 - 14:00||Lunch|
|14:00 - 14:25||Contributed Talk: Robert Bamler, Structured Black Box Variational Inference for Latent Time Series Models|
|14:30 - 15:15||Invited talk: Mehryar Mohri|
|15:15 - 15:45||Afternoon Coffee Break|
|15:45 - 16:10||Contributed Talk: Thang Bui, Online Variational Bayesian Inference: Algorithms for Sparse Gaussian Processes and Theoretical Bounds|
|16:15 - 17:00||Invted Speaker: Vijay M. Janakiraman|
|17:00 - 17:05||Closing Remarks|
We invite researchers to submit both theoretical and applied work on time series analysis, modeling, and algorithms, along with their applications. Papers submitted to the workshop should be up to four pages long excluding references and in ICML 2017 format. As the review process is not blind, authors can reveal their identity in their submissions. All inquiries may be sent to firstname.lastname@example.org .
Submissions page: Times Series Workshop 2017.
Note on open dataset submissions: In order to promote new and innovative research in time series research, we plan to accept a small number of high quality time series dataset contributions. These submissions should be accompanied by a clear and detailed description of the dataset, some potential questions and applications that arise from it, as well as discussion on why the data cannot be sufficiently modeled using traditional batch learning techniques. Preliminary empirical investigations conveying any insight about the data will increase the quality of the submission.
Paper Submission Deadline: June 16, 2017, 11:59 PM PST
Author Notification: June 23, 2017, 11:59 PM PST
Final Version: July 23, 2017, 11:59 PM PST
Workshop: August 11, 2017