Aller au contenu

Toby Dylan Hocking

Professeur, Faculté des sciences
FAC. SCIENCES Informatique

Présentation

Sujet de recherche

Computer Science and Statistics

Disciplines de recherche

Computer Science

Mots-clés

machine learning, statistical software, optimization

Intérêts de recherche

Fast, accurate, and interpretable algorithms for learning from large data, using continuous optimization (clustering, regression, ranking, classification) and discrete optimization (changepoint detection, dynamic programming). The main application domains for these algorithms are genomics, neuroscience, medicine, microbiome, cybersecurity, robotics, satellite/sonar imagery, climate/carbon modeling.

Langues parlées et écrites

Anglais, Français

Diplômes

(2012). Algorithmes d'apprentissage et logiciels pour la statistique, avec applications à la bioinformatique (Doctorate, Docteur). Ecole Normale Supérieure de Cachan.

(2010). A Bayesian Outlier Criterion to Detect SNPs under Selection in Large Data Sets (Master's Thesis, Master). Université de Paris 6-Pitié-Salpêtrière.

(2006). Chromosomal copy number analysis using SNP microarrays and a binomial test statistic (Bachelor's, Bachelor of Arts). University of California, Berkeley.

Expérience académique

Tenured Associate Professor. (2024-). Université de Sherbrooke. Canada.

Tenure-Track Assistant Professor. (2018-2024). Northern Arizona University. United States of America.

Financement

  • Grant. (Awarded). Co-investigator. Addressing Structural Disparities in Autism Spectrum Disorder through Analysis of Secondary Data (ASD3). US National Institute of Mental Health. 455 660 $. (2023-2027)
  • Grant. (Awarded). Co-investigator. MIM: Discovering in reverse – using isotopic translation of omics to reveal ecological interactions in microbiomes.. National Science Foundation (USA). URoL-Understanding the Rules of Life. 3 000 000 $. (2021-2026)
  • Grant. (Awarded). Collaborator. Friends and Foes: microbial interactions and soil biogeochemistry after 23 years of experimental warming. United States Department of Energy. 3 600 000 $. (2022-2025)
  • Grant. (Awarded). Principal Investigator. POSE: Phase II: Expanding the data.table ecosystem for efficient big data manipulation in R. National Science Foundation (USA). Pathways to Enable Open-Source Ecosystems (POSE). 731 881 $. (2023-2025)
  • Grant. (Awarded). Principal Investigator. Efficient algorithms and software for change-point detection. DATAIA (ENS Paris-Saclay, France). Appel à Professeurs Invités. 25 500 $. (2025-2025)
  • Grant. (Awarded). Collaborator. Microbes Persist: Systems Biology of the Soil Microbiome. United States Department of Energy. 819 000 $. (2022-2025)
  • Grant. (Awarded). Principal Investigator. Université de Sherbrooke startup fund. University of Sherbrooke. Startup. 30 000 $. (2024-2025)
  • Grant. (Completed). Collaborator. MMD-DCI Research, Development, & Leadership. Missouri Department of Elementary and Secondary Education. 1 509 570 $. (2021-2023)
  • Grant. (Completed). Principal Investigator. Machine learning algorithms for understanding physically unclonable functions based on resistive memory devices. Air Force Office of Scientific Research (Washington, DC). Summer Faculty Fellowship. 20 000 $. (2021-2021)
  • Grant. (Completed). Principal Investigator. RcppDeepState: an easy way to fuzz test compiled code in R packages. R consortium. R Consortium funded projects. 34 000 $. (2020-2020)

Publications

Articles de revue

  • Bodine, C. S.* and Buscombe, D. and Hocking, T. D. (2024). Automated River Substrate Mapping From Sonar Imagery With Machine Learning. Journal of Geophysical Research: Machine Learning and Computation 1 (3), (Published).
  • Kaufman, Jacob M* and Stenberg, Alyssa J* and Hocking, Toby D. (2024). Functional Labeled Optimal Partitioning. Journal of Computational and Graphical Statistics 1--8. (Published).
  • Tao, Feng* and Houlton, Benjamin Z and Frey, Serita D and Lehmann, Johannes and Manzoni, Stefano and Huang, Yuanyuan and Jiang, Lifen and Mishra, Umakant and Hungate, Bruce A and Schmidt, Michael WI and Markus Reichstein and Nuno Carvalhais and Philippe Ciais and Ying-Ping Wang and Bernhard Ahrens and Gustaf Hugelius and Toby D. Hocking and Xingjie Lu and Zheng Shi and Kostiantyn Viatkin and Ronald Vargas and Yusuf Yigini and Christian Omuto and Ashish A. Malik and Guillermo Peralta and Rosa Cuevas-Corona and Luciano E. Di Paolo and Isabel Luotto and Cuijuan Liao and Yi-Shuang Liang and Vinisa S. Saynes and Xiaomeng Huang and Yiqi Luo. (2024). Reply to: Model uncertainty obscures major driver of soil carbon. Nature 627 (8002), E4--E6. (Published).
  • Hocking, Toby Dylan and Srivastava, Anuraag*. (2023). Labeled optimal partitioning. Computational Statistics 38 461--480. (Published).
  • Feng Tao* and Yuanyuan Huang and Bruce A. Hungate and Stefano Manzoni and Serita D. Frey and Michael W. I. Schmidt and Markus Reichstein and Nuno Carvalhais and Philippe Ciais and Lifen Jiang and Johannes Lehmann and Umakant Mishra and Gustaf Hugelius and Toby D. Hocking and Xingjie Lu and Zheng Shi and Kostiantyn Viatkin and Ronald Vargas and Yusuf Yigini and Christian Omuto and Ashish A. Malik and Guillermo Perualta and Rosa Cuevas-Corona and Luciano E. Di Paolo and Isabel Luotto and Cuijuan Liao and Yi-Shuang Liang and Vinisa S. Saynes and Xiaomeng Huang and Yiqi Luo. (2023). Microbial carbon use efficiency promotes global soil carbon storage. Nature 618 981–985. (Published).
  • Jonathan Hillman* and Toby Dylan Hocking. (2023). Optimizing ROC Curves with a Sort-Based Surrogate Loss for Binary Classification and Changepoint Detection. Journal of Machine Learning Research 24 (70), 1--24. (Published).
  • Harshe, Karl* and Williams, Jack R. and Hocking, Toby D. and Lerner, Zachary F. (2023). Predicting Neuromuscular Engagement to Improve Gait Training With a Robotic Ankle Exoskeleton. IEEE Robotics and Automation Letters 8 (8), 5055-5060. (Published).
  • Runge, Vincent and Hocking, Toby Dylan and Romano, Gaetano* and Afghah, Fatemeh and Fearnhead, Paul and Rigaill, Guillem. (2023). gfpop: An R Package for Univariate Graph-Constrained Change-Point Detection. Journal of Statistical Software 106 (6), 1–39. (Published).
  • Chaves, Ana Paula and Egbert, Jesse and Hocking, Toby and Doerry, Eck and Gerosa, Marco Aurelio. (2022). Chatbots Language Design: The Influence of Language Variation on User Experience with Tourist Assistant Chatbots. ACM Trans. Comput.-Hum. Interact. 29 (2), (Published).
  • Hocking, Toby Dylan and Rigaill, Guillem and Fearnhead, Paul and Bourque, Guillaume. (2022). Generalized Functional Pruning Optimal Partitioning (GFPOP) for Constrained Changepoint Detection in Genomic Data. Journal of Statistical Software 101 (10), 1–31. (Published).
  • Joseph Vargovich* and Toby Dylan Hocking. (2022). Linear time dynamic programming for computing breakpoints in the regularization path of models selected from a finite set. Journal of Computational and Graphical Statistics 31 (2), 313--323. (Published).
  • Mihaljevic, Joseph R and Borkovec, Seth and Ratnavale, Saikanth and Hocking, Toby D and Banister, Kelsey E and Eppinger, Joseph E and Hepp, Crystal and Doerry, Eck. (2022). SPARSEMODr: Rapidly simulate spatially explicit and stochastic models of COVID-19 and other infectious diseases. Biology Methods and Protocols 7 (1), bpac022. (Published).
  • Avinash Barnwal* and Hyunsu Cho and Toby Hocking. (2022). Survival Regression with Accelerated Failure Time Model in XGBoost. Journal of Computational and Graphical Statistics 31 (4), 1292--1302. (Published).
  • Atiyeh Fotoohinasab* and Toby Hocking and Fatemeh Afghah. (2021). A greedy graph search algorithm based on changepoint analysis for automatic QRS complex detection. Computers in Biology and Medicine 130 104208. (Published).
  • Abraham, Andrew J.* and Prys-Jones, Tomos O.* and De Cuyper, Annelies and Ridenour, Chase and Hempson, Gareth P. and Hocking, Toby and Clauss, Marcus and Doughty, Christopher E. (2021). Improved estimation of gut passage time considerably affects trait-based dispersal models. Functional Ecology 35 (4), 860-869. (Published).
  • Liehrmann, Arnaud* and Rigaill, Guillem and Hocking, Toby Dylan. (2021). Increased peak detection accuracy in over-dispersed {ChIP-seq} data with supervised segmentation models. BMC Bioinformatics 22 (323), (Published).
  • Toby Dylan Hocking. (2021). Wide-to-tall Data Reshaping Using Regular Expressions and the nc Package. The R Journal 13 (1), 69--82. (Published).
  • Toby Dylan Hocking and Guillem Rigaill and Paul Fearnhead and Guillaume Bourque. (2020). Constrained Dynamic Programming and Supervised Penalty Learning Algorithms for Peak Detection in Genomic Data. Journal of Machine Learning Research 21 (87), 1--40. (Published).
  • Toby Dylan Hocking. (2019). Comparing namedCapture with other R packages for regular expressions. The R Journal 11 (2), 328--346. (Published).
  • Carson Sievert* and Susan VanderPlas* and Jun Cai* and Kevin Ferris* and Faizan Uddin Fahad Khan* and Toby Dylan Hocking. (2019). Extending ggplot2 for Linked and Animated Web Graphics. Journal of Computational and Graphical Statistics 28 (2), 299-308. (Published).
  • Jewell, Sean W* and Hocking, Toby Dylan and Fearnhead, Paul and Witten, Daniela M. (2019). Fast nonconvex deconvolution of calcium imaging data. Biostatistics 21 (4), 709-726. (Published).

Articles de conférence

  • Sweeney, Nathaniel* and Xu, Caroline and Shaw, Joseph A. and Hocking, Toby D. and Whitaker, Bradley M. (2023). Insect Identification in Pulsed Lidar Images Using Changepoint Detection Algorithms. 2023 Intermountain Engineering, Technology and Computing (IETC). 93-97. (Published).
  • Barr, Joseph R and Hocking, Toby D and Morton, Garinn and Thatcher, Tyler and Shaw, Peter. (2022). Classifying Imbalanced Data with AUM Loss. 2022 Fourth International Conference on Transdisciplinary AI (TransAI). 135--141. (Published).
  • Barr, Joseph R and Shaw, Peter and Abu-Khzam, Faisal N and Thatcher, Tyler and Hocking, Toby Dylan. (2022). Graph embedding: A methodological survey. 2022 Fourth International Conference on Transdisciplinary AI (TransAI). 142--148. (Published).
  • Hocking, Toby D and Barr, Joseph R and Thatcher, Tyler. (2022). Interpretable linear models for predicting security vulnerabilities in source code. 2022 Fourth International Conference on Transdisciplinary AI (TransAI). 149--155. (Published).
  • Kolla, Akhila Chowdary* and Groce, Alex and Hocking, Toby Dylan. (2021). Fuzz Testing the Compiled Code in R Packages. 2021 IEEE 32nd International Symposium on Software Reliability Engineering (ISSRE). 300-308. (Published).
  • Fotoohinasab, Atiyeh* and Hocking, Toby and Afghah, Fatemeh. (2020). A Graph-Constrained Changepoint Learning Approach for Automatic QRS-Complex Detection. 2020 54th Asilomar Conference on Signals, Systems, and Computers. 950-954. (Published).
  • Fotoohinasab, Atiyeh* and Hocking, Toby and Afghah, Fatemeh. (2020). A Graph-constrained Changepoint Detection Approach for ECG Segmentation. 2020 42nd Annual International Conference of the IEEE Engineering in Medicine Biology Society (EMBC). 332-336. (Published).
  • Toby Dylan Hocking and Guillaume Bourque. (2020). Machine Learning Algorithms for Simultaneous Supervised Detection of Peaks in Multiple Samples and Cell Types. Proc. Pacific Symposium on Biocomputing. 367--378. (Published).

Autres contributions

Activités de collaboration internationale

  • Research advisor. United States of America. I was professor at Northern Arizona University, 2018-2024. When I moved to Sherbrooke in May 2024, I have kept working with my students and collaborators there. I put end date Aug 2027 because that is when my last funded project there ends.
  • Collaborator. France. Since my PHD in Paris, I have maintained collaborations with several people in Europe, especially Guillem RIGAILL, with whom I have co-authored several papers on the subject of optimal change-point detection algorithms for sequential data sets. I have received a travel grant to go to Paris in 2025 to work on optimal change-point algorithms with Charles TRUONG.