I am moving to industry!

I will be working at VastData on data management and other fun things.

If looking for my graduate class on vector databases, find it here: CSC 2233.

About Me

My research interests are broad, and include distributed data systems, efficient machine learning algorithms, ML applications, and edge intelligence. Most recently, I've been working on vector databases and approximate nearest neighbour search. Before that I've worked extensively on managing, computing over, learning from, and analyzing geo-distributed data. Previous work includes ML applications in pervasive health monitoring and in computer systems, SSD workload analysis and characterization, supervised learning for clinical gait analysis, anomaly detection in multivariate time series for datacenter monitoring, and compressing deep neural networks to reduce inference times.

I recently joined the Department of Computer Science at the University of Toronto as Research Associate. Before that, I was an assistant professor at York University and a limited-term assistant professor at the University of Toronto. I received my Ph.D. in 2017 from the Computer Science Department at the Technion - Israel Institute of Technology. I also have extensive professional background from my industry days.

Contact

  • Email: mgabel (-at-) cs.toronto.edu
  • UToronto Office: BA5211
    Bahen Centre for Information Technology
    40 St. George Street
    Toronto, Ontario M5S 2E4

Publications and Code

[Google Scholar]
  • Metadata unification in open data with Gnomon. C. Christodoulakis, M. Gabel, and A. D. Brown. 28th International Conference on Extending Database Technology (EDBT), 2025. To appear.
  • FOSI: Hybrid First and Second Order Optimization. H. Sivan, M. Gabel, and A. Schuster. The Twelfth International Conference on Learning Representations (ICLR), 2024.
    [arXiv] [github]
  • Falcon: Live Reconfiguration for Stateful Stream Processing on the Edge. P. Mishra, N. Bore, B. Ramprasad, M. Thiessen, M. Gabel, A. Veith, O. Balmau, and E. de Lara. The Ninth ACM/IEEE Symposium on Edge Computing (SEC), 2024. Best Paper Award.
    [ieee]
  • Towards optimal remote JIT compilation scheduling for the JVM. N. Sreekumar, R. Kha, A. Khrabrov, E. de Lara, A. D. Brown, M. Gabel, and M. Pirvu. The 2nd Workshop on Hot Topics in System Infrastructure (HotInfra), Co-located With SOSP, 2024.
  • PORTEND: A Joint Performance Model for Partitioned Early-Exiting DNNs. M. Ebrahimi, A. da Silva Veith, M. Gabel, and E. de Lara. The 29th IEEE International Conference on Parallel and Distributed Systems (ICPADS), 2023.
    [ieee]
  • Data Management Systems for the Hierarchical Edge. S. H. Mortazavi, M. Salehe, M. Gabel, and E. de Lara. ACM GetMobile: Mobile Computing and Communications, 27(2), 2023.
    [acm]
  • Starlight: Fast Container Provisioning on the Edge and over the WAN. J. L. Chen, D. Liaqat, M. Gabel, and E. de Lara. 19th USENIX Symposium on Networked Systems Design and Implementation (NSDI), 2022.
    [paper] [github] [short video] [full video] [usenix]
  • AutoMon: Automatic Distributed Monitoring for Arbitrary Multivariate Functions. H. Sivan, M. Gabel, and A. Schuster. Proceedings of the 2022 ACM SIGMOD International Conference on Management of Data (SIGMOD), 2022.
    [paper] [video] [github]
  • Shepherd: Seamless Stream Processing on the Edge. B. Ramprasad, P. Mishra, M. Thiessen, H. Chen, A. da Silva Veith, M. Gabel, O. Balmau, A. Chow, and E. de Lara. The Seventh ACM/IEEE Symposium on Edge Computing (SEC), 2022.
  • Optimizing Data Collection in Deep Reinforcement Learning. J. Gleeson, D. Snider, M. Gabel, E. de Lara, and G. Pekhimenko. Third Workshop on Benchmarking Machine Learning Workloads on Emerging Hardware (MLBench 2022), held with Fifth Conference on Machine Learning and Systems (MLSys), 2022.
  • Combining DNN Partitioning and Early Exit. M. Ebrahimi, A. da Silva Veith, M. Gabel, and E. de Lara. 5th International Workshop on Edge Systems, Analytics and Networking (EdgeSys 2022), in conjunction with ACM EuroSys 2022.
    [paper] [acm]
  • Unobtrusive Monitoring of COPD Patients using Speech Collected from Smartwatches in the Wild. T. Sedaghat, S. Liaqat, D. Liaqat, R. Wu, A. Gershon, T. Son, T. H. Falk, M. Gabel, A. Mariakakis, and E. de Lara. WristSense 2022: 8th Workshop on Sensing Systems and Applications using Wrist Worn Smart Devices, Co-located with IEEE PerCom.
    [ieee] [github]
  • Hindsight is 20/20: Retrospective Lessons for Conducting Longitudinal Wearable Sensing Studies. S. Liaqat, D. Liaqat, T. Son, A. Gershon, M. Gabel, R. Wu, and E. de Lara. First International Workshop on Negative Results in Pervasive Computing (PerFail), co-located with IEEE PerCom 2022. Best Paper Award.
    [paper] [video]
  • Remote COPD Severity and Exacerbation Detection Using Heart Rate and Activity Data Measured from a Wearable Device. A. Tiwari, S. Liaqat, D. Liaqat, M. Gabel, E. de Lara, and T. H. Falk. 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2021.
    [ieee]
  • A Distance-Based Scheme for Reducing Bandwidth in Distributed Geometric Monitoring. Y. Alfassi, M. Gabel, G. Yehuda, and D. Keren. 37th IEEE International Conference on Data Engineering (ICDE), 2021.
    [paper] [video]
  • CoughWatch: Real-world Cough Detection Using Smartwatches. D. Liaqat, S. Liaqat, J. L. Chen, T. Sedaghat, M. Gabel, F. Rudzicz, and E. de Lara. 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.
    [ieee]
  • RL-Scope: Cross-stack Profiling for Deep Reinforcement Learning Workloads. J. Gleeson, S. Krishnan, M. Gabel, V. J. Reddi, E. de Lara, and G. Pekhimenko. Fourth Conference on Machine Learning and Systems (MLSys), 2021.
    [paper] [short video] [full video] [github] [site]
  • SSD-Based Workload Characteristics and Their Performance Implications. G. Yadgar, M. Gabel, S. Jaffer, and B. Schroeder. ACM Transactions on Storage (ToS), 17(1), 2021.
    [acm]
  • Skin tone, Confidence, and Data Quality of Heart Rate Sensing in WearOS Smartwatches. I. Ray, D. Liaqat, M. Gabel, and E. de Lara. 6th IEEE PerCom International workshop on Pervasive Health Technologies (PerHealth 2021).
    [paper] [video]
  • WristO2: Reliable Peripheral Oxygen Saturation Readings from Wrist-Worn Pulse Oximeters. C. Phillips, D. Liaqat, M. Gabel, and E. de Lara. WristSense 2021: 7th Workshop on Sensing Systems and Applications Using Wrist Worn Smart Devices, co-located with IEEE PerCom. Honorable mention.
    [paper]
  • Sustainable Computing on the Edge: A Systems Dynamics Perspective. B. Ramprasad, M. Gabel, A. da Silva Veith, and E. de Lara. Proceedings of the 22th International Workshop on Mobile Computing Systems and Applications (HotMobile), 2021.
    [acm]
  • It's Not What Machines Can Learn, It's What We Cannot Teach. G. Yehuda, M. Gabel, and A. Schuster. 37th International Conference on Machine Learning (ICML), 2020.
    [paper] [video] [supplemental material] [arXiv]
  • Pytheas: Pattern-based Table Discovery in CSV Files. C. Christodoulakis, E. B. Munson, M. Gabel, A. D. Brown, and R. J. Miller. 46th International Conference on Very Large Data Bases (VLDB), 2020.
    [paper] [video] [github]
  • Feather: Hierarchical Querying for the Edge. S. H. Mortazavi, M. Salehe, M. Gabel, and E. de Lara. The Fifth ACM/IEEE Symposium on Edge Computing (SEC), 2020. Honorable mention.
    [paper] [video]
  • Incremental Sensitivity Analysis for Kernelized Models. H. Sivan, M. Gabel, and A. Schuster. The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2020.
    [paper] [video] [code]
  • Online Linear Models for Edge Computing. H. Sivan, M. Gabel, and A. Schuster. The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), 2019.
    [paper]
  • Wearbreathing: Real World Respiratory Rate Monitoring Using Smartwatches. D. Liaqat, M. Abdalla, P. Abed-Esfahani, M. Gabel, T. Son, R. Wu, A. Gershon, F. Rudzicz, and E. de Lara. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT / UbiComp), 3(3), 2019.
    [paper]
  • Taming Momentum in a Distributed Asynchronous Environment. I. Hakimi, S. Barkai, M. Gabel, and A. Schuster. arXiv preprint arXiv:1907.11612, 2019.
    [arXiv]
  • Reconfigurable Streaming for the Mobile Edge. A. Tiwari, B. Ramprasad, S. H. Mortazavi, M. Gabel, and E. de Lara. Proceedings of the 20th International Workshop on Mobile Computing Systems and Applications (HotMobile), 2019.
    [paper]
  • Anarchists, Unite: Practical Entropy Approximation for Distributed Streams. M. Gabel, D. Keren, and A. Schuster. 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2017.
    [paper] [short video]
  • One for All and All for One: Simultaneous Approximation of Multiple Functions over Distributed Streams. A. Lazerson, M. Gabel, D. Keren, and A. Schuster. 11th ACM International Conference on Distributed and Event-Based Systems (DEBS), 2017.
    [paper]
  • On the Equivalence of the LC-KSVD and the D-KSVD Algorithms. I. Kviatkovsky, M. Gabel, E. Rivlin, and I. Shimshoni. IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 39(2):411-416, 2017.
    [paper]
  • Avoiding the Streetlight Effect: I/O Workload Analysis with SSDs in Mind. G. Yadgar, M. Gabel. 8th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage), 2016.
    [paper]
  • Monitoring Least Squares Models of Distributed Streams. M. Gabel, D. Keren, and A. Schuster. 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2015.
    [paper]
  • Latent Fault Detection With Unbalanced Workloads. M. Gabel, K. Sato, D. Keren, S. Matsuoka, and A. Schuster. Event Processing, Forecasting and Decision-Making in the Big Data Era (EPForDM) workshop, held in conjunction with EDBT, 2015.
    [paper]
  • Communication-efficient Distributed Variance Monitoring and Outlier Detection for Multivariate Time Series. M. Gabel, D. Keren, and A. Schuster. 28th IEEE International Parallel & Distributed Processing Symposium (IPDPS), 2014.
    [paper]
  • Communication-efficient Outlier Detection for Scale-out Systems. M. Gabel, D. Keren, and A. Schuster. First International Workshop on Big Dynamic Distributed Data (BD3), held at the 39th International Conference on Very Large Data Bases (VLDB), 2013.
  • Full Body Gait Analysis With Kinect. M. Gabel, R. Gilad-Bachrach, E. Renshaw, and A. Schuster. 34th Annual International Conference of the IEEE in Engineering in Medicine and Biology Society (EMBC), 2012.
    [paper]
  • Latent Fault Detection in Large Scale Services. M. Gabel, A. Schuster, R.-G. Bachrach, and N. Bjørner. 42nd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), 2012.
    [paper] [master thesis]

Students

I have trained over a dozen graduate students, both in official supervisory capacity and unofficially as mentor. Former students have since found positions as researchers, software developers, and data scientists.

I do not have any open positions for students or post-docs.

Teaching

  • Winter 2025: CSC 2233 - Topics in Storage Systems: Vector Databases (University of Toronto)
  • Winter 2023: EECS 3421 - Introduction to Database Systems (York University)
  • Winter 2022: CSC B58 - Computer Organization (University of Toronto)
  • Winter 2021: CSC B58 - Computer Organization (University of Toronto)
  • Winter 2020: CSC B58 - Computer Organization (University of Toronto)
  • Winter 2019: CSC B58 - Computer Organization (University of Toronto)
  • Fall 2018: CSC 494/2699 - Independent Study: SSD-based workload characteristics (University of Toronto)
  • Previously in Technion as TA: Intro to Computer Science, Intro to Computer Science - C language, Operating Systems

Academic Leadership

Organizing:

  • Program Co-Chair, SYSTOR 2022
    • Poster Chair, SEC 2020
  • Poster Co-chair, MobiSys 2020

Program committees:

  • Program Committee, NeurIPS 2024
  • External Review Committee, ASPLOS 2024
  • Program Committee, Cluster 2023
  • Program Committee, NeurIPS 2022
  • Program Committee, ICML 2022
  • Program Committee, OSDI 2021
  • External Review Committee, ASPLOS 2021
  • Program Committee (Distinguished Reviewer), SYSTOR 2021
  • Program Committee, ATC 2020
  • Program Committee, ECML PKDD 2020
  • Program Committee, SYSTOR 2020
  • Program Committee, HotEdge 2020
  • Program Committee, EdgeSys 2020
  • Program Committee, ATC 2019
  • Program Committee, CIKM 2018

Reviewed for: ATC 2015-2017, KDD 2016-2018, OSDI 2018, SDM 2015-2017, EuroSys 2012, 2015, 2017, IPDPS 2013, BigData 2017, DEBS 2016, EDBT 2016, FAST 2013, HotCloud 2013-2014, ICS 2013, SOCC 2014.

Industry Experience

Before returning to graduate school, I spent a decade in industry in multiple leadership and development roles . I worked on embedded systems, computer graphics, file system and kernel development, DSP development, image processing, and more. My roles included algorithm R&D, software development, API design, performance optimization, team lead, and project planning.