Dr Adam M Sykulski
|Themes||Multivariate and High Dimensional Data, Stochastic Modelling and Time Series|
I am a Research Associate at University College London working with Professor Sofia Olhede on high dimensional models for multivariate time series analysis. I am particularly interested in constructing new methods for modelling and estimating dependence structure in large heterogeneous spatiotemporal processes. This methodology addresses numerous challenges present in modern 'Big Data' problems, for example: irregular sampling, nonstationarity and geometrical considerations such as non-Euclidean coordinates. Check out my latest paper (details below) on capturing dependence structure in multivariate time series, where we have extended and improved efficient likelihood inference for complex-valued time series.
I have applied my research to oceanographic data, which has important implications in our understanding of the climate. In particular, I am implementing our methods on data from the Global Drifter Program: a large database of worldwide satellite-tracked freely-drifting instruments known as 'drifters'. We construct physically-motivated stochastic processes to help us summarise the complicated structures observed. This allows us to make insightful new findings which improves climate modelling and our ability to respond to environmental threats such as oil spills.
Please get in touch if you're interested in time series analysis, spatiotemporal data, mutlivariate dependence structure, likelihood inference, spectral-domain analysis, and applications of statistics in oceanography and climate.
I also have an active research interest in decision theory problems related to the multi-armed bandit problem. In particular, I am interested in on-line tuning of the exploration-exploitation tradeoff and also extensions to multi-player problems which bring in ideas from game theory.
Time Series Analysis, Spatiotemporal Processes, Complex-valued Proceses, Applications in Oceonography and Neuroscience, Decision Theory, Game Theory, Tennis.
- Sykulski, A.M., Olhede S.C., Lilly J.M. and Early J.J. (2013) The Whittle likelihood for complex-valued time series. arXiv preprint, arXiv:1306.5993.
- Olhede, S.C., Sykulski, A.M. and Pavliotis, G.A. (2009) Frequency domain estimation of integrated volatility for Ito processes in the presence of market-microstructure noise. SIAM - Multiscale Modeling and Simulation, 8 (2). pp. 393-427.
- Sykulski, A.M., Adams, N.M. and Jennings, N.R. (2010) On-line adaptation of exploration in the one-armed bandit with covariates problem. In: 9th International Conference on Machine Learning and Applications (ICMLA 2010), 12th-14th Dec 2010, Washington DC, USA. pp. 459-464.
- Munoz de Cote, E., Sykulski, A.M., Chapman, A.C. and Jennings, N.R. (2010) Automated planning in repeated adversarial games. In: 26th Conference on Uncertainty in Artificial Intelligence (UAI 2010), 8th-11th July 2010, Catalina Island, California, USA. pp. 376-383.
Page last modified on 30 aug 13 12:30