My research focuses on statistical machine learning methodologies for data-driven modeling and discovery. Many fields of discovery – not only in the sciences, engineering, and medicine, but also in the social sciences and increasingly in the humanities – are transitioning from “data-poor” to “data-rich.” The ability to extract knowledge from vast amounts of data lies at the heart of 21st century scholarship. The main research themes I am currently working on are:

• Variational Bayes.
• Hierarchical latent variable models, esp. hidden Markov models, hierarchical Dirichlet processes, Gaussian processes, and variational autoencoders. 
• Applications of machine learning to statistical signal processing, natural language modeling, and human user modeling.

1. Sotirios P. Chatzis, "Latent Subspace Modeling of Sequential Data Under the Maximum Entropy Discrimination Framework," Neurocomputing, in press.
2. Harris Partaourides and Sotirios P. Chatzis, “Deep Learning with t-Exponential Bayesian Kitchen Sinks,” Expert Systems with Applications, vol. 98, pp. 84-92, May 2018.
3. Tania Panayiotou, Sotirios P. Chatzis, and Georgios Ellinas, “Leveraging Statistical Machine Learning to Address Failure Localization in Optical Networks,” IEEE/OSA Journal of Optical Communications and Networking, vol. 10, no. 3, pp. 162-173, March 2018.
4. Anastasios Petropoulos, Sotirios P. Chatzis, Vasilis Siakoulis, and Nikos Vlachogiannakis, “A Stacked Generalization System for Automated FOREX Portfolio Trading,” Expert Systems with Applications, vol. 90, pp. 290-302, Dec. 2017.
5. Anastasios Petropoulos* , Sotirios P. Chatzis*, and Stelios Xanthopoulos, "A hidden Markov model with dependence jumps for predictive modeling of multidimensional time-series," Information Sciences, vol. 412-413, pp. 50-66, Oct. 2017.
6. Harris Partaourides and Sotirios P. Chatzis, “Asymmetric Deep Generative Models,” Neurocomputing, vol. 241, pp. 90-96, June 2017.
7. Tania Panayiotou, Sotirios P. Chatzis, and George Ellinas, "Performance Analysis of a Data-Driven QoT Decision Approach on a Dynamic Multicast-Capable Metro Optical Network," IEEE/OSA Journal of Optical Communications and Networking, vol. 9, no. 1, pp. 98-108, Jan. 2017.
8. Sotirios P. Chatzis, “Maximum Entropy Discrimination Factor Analyzers,” Neurocomputing, vol. 216, pp. 409-415, Dec. 2016.
9. Andreas S. Andreou and Sotirios P. Chatzis, "Software Defect Prediction Using Doubly Stochastic Poisson Processes Driven by Stochastic Belief Networks," Journal of Systems and Software, vol. 122, pp. 72-82, Dec. 2016.
10. Anastasios Petropoulos, Sotirios P. Chatzis, Stelios Xanthopoulos, “A Novel Corporate Credit Rating System Based on Student’s-t Hidden Markov Models,” Expert Systems with Applications, vol. 53, pp. 87-105, July 2016.
11. Sotirios P. Chatzis, Andreas S. Andreou, “Maximum Entropy Discrimination Poisson Regression for Software Reliability Modeling,” IEEE Transactions on Neural Networks and Learning Systems, vol. 26, no. 11, pp. 2689-2701, Nov. 2015.
12. Sotirios P. Chatzis and Dimitrios Kosmopoulos, “A Latent Manifold Markovian Dynamics Gaussian Process,” IEEE Transactions on Neural Networks and Learning Systems, vol. 25, no. 1, pp. 70-83, Jan. 2015.
13. Emmanouil A. Platanios and Sotirios P. Chatzis, “Gaussian Process-Mixture Conditional Heteroscedasticity,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 36, no. 5, pp. 888-900, May 2014.
14. Sotirios P. Chatzis, “A Latent Variable Gaussian Process Model with Pitman-Yor Process Priors for Multiclass Classification,” Neurocomputing, vol. 120, pp. 482-489, Nov. 2013.
15. Sotirios P. Chatzis, “Maximum-Margin Classification of Sequential Data with Infinitely-Long Temporal Dependencies,” Expert Systems with Applications, vol. 40, no. 11, pp. 4519–4527, Sep. 2013.
16. Sotirios P. Chatzis, Yiannis Demiris, “The Infinite-Order Conditional Random Field Model for Sequential Data Modeling,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 6, pp. 1523-1534, June 2013.
17. S. Chatzis, D. Kosmopoulos, P. Doliotis, “A Conditional Random Field-Based Model for Joint Sequence Segmentation and Classification,” Pattern Recognition, vol. 46, no. 6, pp. 1569-1578, June 2013.
18. Sotirios P. Chatzis, “A Markov Random Field-Regulated Pitman-Yor Process Prior for Spatially-Constrained Data Clustering,” Pattern Recognition, vol. 46, no. 6, pp. 1595-1603, June 2013.
19. Sotirios P. Chatzis, Yiannis Demiris, “Nonparametric mixtures of Gaussian processes with power-law behavior,” IEEE Transactions on Neural Networks and Learning Systems, vol. 23, no. 12, pp. 1862-1871, Dec. 2012.
20. Sotirios P. Chatzis, D. Korkinof, and Yiannis Demiris, “A Quantum-Statistical Approach Toward Robot Learning by Demonstration,” IEEE Transactions on Robotics, vol. 28, no. 6, pp. 1371-1381, Dec. 2012.
21. Sotirios P. Chatzis, Dimitrios Korkinof, and Yiannis Demiris, “A Spatially-Constrained Normalized Gamma Process Prior,” Expert Systems with Applications, vol. 39, no. 17, pp. 13019–13025, Dec. 2012.
22. Sotirios P. Chatzis, Yiannis Demiris, “A Reservoir-Driven Non-Stationary Hidden Markov Model,” Pattern Recognition, vol. 45, no. 11, pp. 3985–3996, Nov. 2012.
23. Sotirios P. Chatzis, Yiannis Demiris, “The Echo State Conditional Random Field Model for Sequential Data Modeling,” Expert Systems with Applications, vol. 39, no. 11, pp. 10303–10309, Sep. 2012.
24. Sotirios P. Chatzis, Dimitrios Kosmopoulos, “Visual Workflow Recognition Using a Variational Bayesian Treatment of Multistream Fused Hidden Markov Models,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 22, no. 7, pp. 1076-1086, July 2012.
25. Sotirios P. Chatzis, Dimitrios Korkinof, and Yiannis Demiris, “A nonparametric Bayesian approach toward robot learning by demonstration,” Robotics and Autonomous Systems, vol. 60, no. 6, pp. 789–802, June 2012.
26. Sotirios P. Chatzis, Yiannis Demiris, “A Sparse Nonparametric Hierarchical Bayesian Approach Towards Inductive Transfer for Preference Modeling,” Expert Systems with Applications, vol. 39, no. 8, pp. 7235–7246, June 2012.
27. Sotirios P. Chatzis, Gavriil Tsechpenakis, “A possibilistic clustering approach toward generative mixture models,” Pattern Recognition, vol. 45, no. 5, pp. 1819–1825, May 2012.
28. Sotirios P. Chatzis, Yiannis Demiris, “The Copula Echo State Network,” Pattern Recognition, vol. 45, no. 1, pp. 570-577, Jan. 2012.
29. Sotirios Chatzis, S. Koukas, “Numerical Optimization Using Synergetic Swarms of Foraging Bacterial Populations, Expert Systems with Applications, vol. 38, no. 12, pp. 15332-15343, Nov./Dec. 2011.
30. Sotirios P. Chatzis, Yiannis Demiris, “Echo State Gaussian Process,” IEEE Transactions on Neural Networks, vol. 22, no. 9, pp. 1435-1445, Sep. 2011.
31. Gavriil Tsechpenakis, Sotirios P. Chatzis, “Deformable Probability Maps: Probabilistic Shape and Appearance-based Object Segmentation,” Computer Vision and Image Understanding, vol. 115, no. 8, pp. 1157-1169, Aug. 2011.
32. Sotirios P. Chatzis, “A fuzzy c-means-type algorithm for clustering of data with mixed numeric and categorical attributes employing a probabilistic dissimilarity functional,” Expert Systems with Applications, vol. 38, no. 7, pp. 8684–8689, July 2011.
33. Sotirios P. Chatzis, Dimitrios Kosmopoulos, “A Variational Bayesian Methodology for Hidden Markov Models utilizing Student’s-t Mixtures,” Pattern Recognition, vol. 44, no. 2, pp. 295-306, Feb. 2011.
34. Sotirios P. Chatzis, “Hidden Markov Models with Nonelliptically Contoured State Densities,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 32, no. 12, pp. 2297-2304, Dec. 2010.
35. Sotirios Chatzis, “A method for training finite mixture models under a fuzzy clustering principle,” Fuzzy Sets and Systems, vol. 161, no. 23, pp. 3000-3013, Dec. 2010.
36. Dimitrios Kosmopoulos, Sotirios P. Chatzis, “Robust visual behavior recognition,” IEEE Signal Processing Magazine, vol. 27, no. 5, pp. 34-45, Sep. 2010.
37. Sotirios P. Chatzis, Gabriel Tsechpenakis, “The Infinite Hidden Markov Random Field Model,” IEEE Transactions on Neural Networks, vol. 21, no. 6, pp. 1004-1014, June 2010.
38. Sotirios P. Chatzis, Dimitrios I. Kosmopoulos, Theodora A. Varvarigou, “Robust Sequential Data Modeling Using an Outlier Tolerant Hidden Markov Model,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 9, pp. 1657-1669, Sep. 2009.
39. S. Chatzis, T. Varvarigou, “Factor Analysis Latent Subspace Modeling and Robust Fuzzy Clustering Using t-Distributions,” IEEE Transactions on Fuzzy Systems, vol. 17, no. 3, pp. 505-517, June 2009.
40. D. I. Kosmopoulos, A. Doulamis, A. Makris, N. Doulamis, S. Chatzis, S. E. Middleton, “Vision-Based Production of Personalized Video,” Signal Processing: Image Communication, vol. 24, no. 3, pp. 158-176, March 2009.
41. Sotirios P. Chatzis, Theodora A. Varvarigou, “A Fuzzy Clustering Approach Toward Hidden Markov Random Field Models for Enhanced Spatially Constrained Image Segmentation,” IEEE Transactions on Fuzzy Systems, vol. 16, no. 5, pp. 1351-1361, Oct. 2008.
42. Sotirios Chatzis, Theodora Varvarigou, “Robust Fuzzy Clustering Using Mixtures of Student’s-t Distributions,” Pattern Recognition Letters, vol. 29, no. 13, pp. 1901-1905, Oct. 2008.
43. A. Litke, K. Konstanteli, V. Andronikou, S. Chatzis, T. Varvarigou, “Managing service level agree- ment contracts in OGSA-based Grids,” Future Generation Comp. Syst. vol. 24, no. 4, pp. 245-258, April 2008.
44. Sotirios P. Chatzis, Dimitrios I. Kosmopoulos, Theodora A. Varvarigou, “Signal Modeling and Classification Using a Robust Latent Space Model Based on t Distributions,” IEEE Transactions on Signal Processing, vol. 56, no. 3, pp. 949-963, March 2008.

Top-Tier Computer Science Conference Publications (highly prestigious and competitive)

1. Sotirios P. Chatzis, "Indian Buffet Process Deep Generative Models for Semi-Supervised Classification," Proc. 43rd IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), April 2018.
2. Harris Partaourides* and Sotirios P. Chatzis*, “Deep Network Regularization via Bayesian Inference of Synaptic Connectivity,” J. Kim et al. (Eds.): PAKDD 2017, Part I, LNAI 10234, pp. 30–41, 2017. (Long presentation paper; acceptance rate=9.8%)
3. Sotirios P. Chatzis, “Deep Bayesian Matrix Factorization,” J. Kim et al. (Eds.): PAKDD 2017, Part II, LNAI 10235, pp. 453–464, 2017 (Long presentation paper; acceptance rate=9.8%)
4. Sotirios P. Chatzis, “Recurrent Latent Variable Conditional Heteroscedasticity,” Proc. 42nd IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), pp. 2711-2715, March 2017.
5. Sotirios P. Chatzis, Dimitrios Kosmopoulos, “A Nonparametric Bayesian Approach Toward Stacked Convolutional Independent Component Analysis,” Proc. 15th International IEEE Conference on Computer Vision (IEEE ICCV), Dec. 2015.
6. Sotirios P. Chatzis, “Inducing space Dirichlet process mixture large-margin entity relationship inference in knowledge bases,” Proc. 24th ACM International Conference on Information and Knowledge Management (ACM CIKM), Oct. 2015, pp. 1311-1320.
7. Sotirios P. Chatzis, "Sparse Bayesian Recurrent Neural Networks," Proc. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML/PKDD), Sep. 2015, pp. 359-372.
8. Sotirios P. Chatzis, “Dynamic Bayesian Probabilistic Matrix Factorization,” Proc. 28th AAAI Conference on Artificial Intelligence (AAAI-14), July 2014, pp. 1731-1737.
9. Sotirios P. Chatzis, “Echo-State Conditional Restricted Boltzmann Machines,” Proc. 28th AAAI Conference on Artificial Intelligence (AAAI-14), July 2014, pp. 1738-1744.
10. Sotirios P. Chatzis, “Nonparametric Bayesian Multitask Collaborative Filtering,” Proc. 22nd ACM International Conference on Information and Knowledge Management (ACM CIKM), Oct. 2013, pp. 2149-2158.
11. Sotirios P. Chatzis, “Infinite Markov-Switching Maximum Entropy Discrimination Machines,” Proc. 30th International Conference on Machine Learning (ICML). Journal of Machine Learning Research: Workshop and Conference Proceedings, vol. 28, no. 3, pp. 729-737, June 2013.
12. Sotirios P. Chatzis, Gabriel Tsechpenakis, “The Infinite Hidden Markov Random Field Model,” in Proc. 12th International IEEE Conference on Computer Vision (IEEE ICCV), Oct. 2009, pp. 654-661.
13. Sotirios Chatzis, Dimitrios I. Kosmopoulos, Theodora Varvarigou, “A Robust Approach Towards Sequential Data Modeling and its Application in Automatic Gesture Recognition,” Proc. 33rd IEEE Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), Mar. 2008, pp. 1937-1940.

Other Refereed Conference and Workshop Publications

1. Savvas Zannettou, Sotirios Chatzis, Kostantinos Papadamou, Michael Sirivianos, “The good, the bad and the bait: Detecting and characterizing clickbait videos on YouTube,” Proc. 1st Deep Learning and Security Workshop, May 2018.
2. Tania Panayiotou, Sotirios P. Chatzis, and Georgios Ellinas, “A Probabilistic Approach for Failure Localization,” Proc. 21st International Conference on Optical Network Design and Modeling (ONDM), 2017. (Best Paper Award)
3. Sotirios P. Chatzis, Panayiotis Christodoulou, and Andreas S. Andreou, “Recurrent Latent Variable Networks for Session-Based Recommendation,” Proc. 2nd Workshop on Deep Learning for Recommender Systems (DLRS). ACM, New York, NY, USA, pp. 38-45, 2017. (Oral Presentation)
4. T. Panayiotou, G. Ellinas, and S. Chatzis, "A Data-Driven QoT Decision Approach for Multicast Connections in Metro Optical Networks," Proc. 20th International Conference on Optical Network Design and Modeling (ONDM), 2016.
5. Sotirios P. Chatzis, Dimitrios I. Kosmopoulos, and George M. Papadourakis, “A Nonstationary Hidden Markov Model with Approximately Infinitely-Long Time-Dependencies,” Proc. 10th International Symposium on Visual Computing (ISVC), Dec. 2014, pp. 51-62.
   • An invited extended version of the same paper appears in a Special Issue of the International Journal of Artificial Intelligence Tools, vol. 25, no. 5: 1640001,October 2016.
6. Sotirios P. Chatzis, Dimitrios Kosmopoulos, “A Non-Stationary Infinite Partially-Observable Markov Decision Process,” Proc. 24th International Conference on Artificial Neural Networks (ICANN), Sep. 2014, pp. 355-362.
7. Sotirios P. Chatzis, “A Coupled Indian Buffet Process Model for Collaborative Filtering,” Proc. 4th Asian Conference on Machine Learning (ACML). Journal of Machine Learning Research: Workshop and Conference Proceedings, vol. 25, Nov. 2012, pp. 65–79.
8. Sotirios P. Chatzis, Dimitrios Korkinof, and Yiannis Demiris, “The One-Hidden-Layer Non-parametric Bayesian Kernel Machine,” Proc. 23rd IEEE International Conference on Tools with Artificial Intelligence (ICTAI), Nov. 2011, pp. 825-831.
9. A. Irvine, S. Chatzis, and G. Tsechpenakis, “Which Brainstem Cells Generate the Respiration Cycles?,” Proc. IEEE Int. Symposium on Biomedical Imaging: from Nano to Macro (ISBI), April 2010, pp. 65-68.
10. R.K. Cowen, C. Guigand, C. Cousin, G. Tsechpenakis, S. Chatzis, A. Greer, “An operational In-Situ Ichthyoplankton Imaging System (ISIIS),” Proc. OceanObs, Sep. 2009.
11. S. Chatzis, A. Doulamis, T. Varvarigou, “A Content-Based Image Retrieval Scheme Allowing for Robust Automatic Personalization,” Proc. ACM Conf. Image and Video Retrieval, June 2007, pp. 1-7.

Current

1. Pavlos Nikolaidis: Constrained Bayesian optimization for renewable energy integration in smart power grids.

2. Kyriacos Tolias: Latent variable models for natural language modeling (question-answering systems and document summarizers).

3. Aristotelis Charalambous: Transfer learning methods for neural attention networks applied to natural language processing.

4. Anastasios Antoniadis: Bayesian nonparametrics for deep learning.

5. Ioannis Armenakis: Bayesian statistics applied to ship design. 

6. Ioannis Kourouklides: Reinforcement leaning and stochastic bandits.

Graduated/Upon graduation

1. Harris Partaourides: Latent variable models and amortized variational inference.

• CEI 523: Data Science
• CEI 327: Parallel and Distributed Processing Systems
• CEI 329: Statistical Pattern Recognition and Machine Learning

Ο Δρ. Χατζής είναι Βοηθός Εκδότη (Associate Editor) για τα κορυφαία περιοδικά

• IEEE Transactions on Signal Processing.
• Pattern Recognition.

Είναι επίσης τακτικό μέλος της επιτροπής προγράμματος για κορυφαία venues του τομέα του, περιλαμβανομένων των συνεδρίων:

• ICML
• NIPS
• AISTATS
• ICLR

• IRC-HERMES: Interregional Cultural Heritage Management E-System. Cooperation Programme INTERREG V-B, Balkan-Mediterranean 2014-2020. co-Principal Investigator, 12/2017-12/2019.
• RE-CULT: Promotion and Dissemination of the cultural and natural heritage via the development and institutional support of Religious Tourism in the insular area of Greece and Cyprus. Cooperation Programme INTERREG V-A, Greece-Cyprus 2014-2020. co-Principal Investigator, 12/2017-12/2019.
• NOTRE: Network for Social Computing Research Center. H2020 Twinning programme – TWINN – 2015. co-Principal Investigator, 1/2016-12/2018.
• ReCRED: From Real-world Identities to Privacy-Preserving and Attribute-based CREDentials for Device-centric Access Control. H2020 Digital Security-Access Control. co-Principal Investigator, 5/2015-4/2018.
• NVIDIA Corporation Academic Partnership Program: Donation of one Tesla K40 GPU, to support my project on Bayesian non-parametrics applied to Deep Learning. Worth approx. $5K.