Structured Gotos are (Slightly) Harmful
Sennesh, E., & Gil, Y. (2016). Structured gotos are (slightly) harmful. In Proceedings of the 31st Annual ACM Symposium on Applied Computing (pp. 1784–1789).
CV
Education
- B.S. in Computer Science, University of Massachusetts Amherst, 2011
- M.S. in Computer Science, Technion Israel Institute of Technology, 2015
- Ph.D, Northeastern University (currently in progress)
Publications
Créer de tête de nombreux mots de passe inviolables et inoubliables
Nicolas Blanchard, Leila Gabasova, Ted Selker, Eli Sennesh. Créer de tête de nombreux mots de passe inviolables et inoubliables. ALGOTEL 2018 - 20èmes Rencontres Francophones sur les Aspects Algorithmiques des Télécommunications, May 2018, Roscoff, France. 2018.
Combinators for Modeling and Inference
Sennesh, E., Wu, H., & van de Meent, J.-W. (2018). Combinators for Modeling and Inference.
Composing Modeling and Inference Operations with Probabilistic Program Combinators
Sennesh, E., Scibior, A., Wu, H., & van de Meent, J.-W. (2018). Composing Modeling and Inference Operations with Probabilistic Program Combinators.
Amortized Population Gibbs Samplers with Neural Sufficient Statistics
@InProceedings{pmlr-v119-wu20h, title = {Amortized Population {G}ibbs Samplers with Neural Sufficient Statistics}, author = {Wu, Hao and Zimmermann, Heiko and Sennesh, Eli and Le, Tuan Anh and Van De Meent, Jan-Willem}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {10421--10431}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/wu20h/wu20h.pdf}, url = {https://proceedings.mlr.press/v119/wu20h.html}, abstract = {We develop amortized population Gibbs (APG) samplers, a class of scalable methods that frame structured variational inference as adaptive importance sampling. APG samplers construct high-dimensional proposals by iterating over updates to lower-dimensional blocks of variables. We train each conditional proposal by minimizing the inclusive KL divergence with respect to the conditional posterior. To appropriately account for the size of the input data, we develop a new parameterization in terms of neural sufficient statistics. Experiments show that APG samplers can be used to train highly-structured deep generative models in an unsupervised manner, and achieve substantial improvements in inference accuracy relative to standard autoencoding variational methods.} }
Learning a Deep Generative Model like a Program: the Free Category Prior
@article{sennesh2020learning, title={Learning a Deep Generative Model like a Program: the Free Category Prior}, author={Sennesh, Eli}, journal={arXiv preprint arXiv:2011.11063}, year={2020} }
Neural Topographic Factor Analysis for fMRI Data
@inproceedings{NEURIPS2020_8c3c27ac, author = {Sennesh, Eli and Khan, Zulqarnain and Wang, Yiyu and Hutchinson, J Benjamin and Satpute, Ajay and Dy, Jennifer and van de Meent, Jan-Willem}, booktitle = {Advances in Neural Information Processing Systems}, editor = {H. Larochelle and M. Ranzato and R. Hadsell and M.F. Balcan and H. Lin}, pages = {12046--12056}, publisher = {Curran Associates, Inc.}, title = {Neural Topographic Factor Analysis for fMRI Data}, url = {https://proceedings.neurips.cc/paper/2020/file/8c3c27ac7d298331a1bdfd0a5e8703d3-Paper.pdf}, volume = {33}, year = {2020} }
Learning proposals for probabilistic programs with inference combinators
@InProceedings{pmlr-v161-stites21a, title = {Learning proposals for probabilistic programs with inference combinators}, author = {Stites, Sam and Zimmermann, Heiko and Wu, Hao and Sennesh, Eli and van de Meent, Jan-Willem}, booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence}, pages = {1056--1066}, year = {2021}, editor = {de Campos, Cassio and Maathuis, Marloes H.}, volume = {161}, series = {Proceedings of Machine Learning Research}, month = {27--30 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v161/stites21a/stites21a.pdf}, url = {https://proceedings.mlr.press/v161/stites21a.html}, abstract = {We develop operators for construction of proposals in probabilistic programs, which we refer to as inference combinators. Inference combinators define a grammar over importance samplers that compose primitive operations such as application of a transition kernel and importance resampling. Proposals in these samplers can be parameterized using neural networks, which in turn can be trained by optimizing variational objectives. The result is a framework for user-programmable variational methods that are correct by construction and can be tailored to specific models. We demonstrate the flexibility of this framework by implementing advanced variational methods based on amortized Gibbs sampling and annealing.} }
Interoception as modeling, allostasis as control
@article{sennesh2022interoception, title={Interoception as modeling, allostasis as control}, author={Sennesh, Eli and Theriault, Jordan and Brooks, Dana and van de Meent, Jan-Willem and Barrett, Lisa Feldman and Quigley, Karen S}, journal={Biological Psychology}, volume={167}, pages={108242}, year={2022}, publisher={Elsevier} }
A Computational Neural Model for Mapping Degenerate Neural Architectures
@article{khan2022computational, title={A computational neural model for mapping degenerate neural architectures}, author={Khan, Zulqarnain and Wang, Yiyu and Sennesh, Eli and Dy, Jennifer and Ostadabbas, Sarah and van de Meent, Jan-Willem and Hutchinson, J Benjamin and Satpute, Ajay B}, journal={Neuroinformatics}, pages={1--15}, year={2022}, publisher={Springer} }
A Probabilistic Generative Model of Free Categories
@article{sennesh2022probabilistic, title={A Probabilistic Generative Model of Free Categories}, author={Sennesh, Eli and Xu, Tom and Maruyama, Yoshihiro}, journal={arXiv preprint arXiv:2205.04545}, year={2022} }
Service and leadership
- Program Committee Member in ACM Symposium on Applied Computing 2017
Talks
Neuroscience, Sloppiness, and Ground Truth
Paper presentation at Psychologists, Engineers, and Neuroscientists seminar, Northeastern University, Boston MA, USA
Concepts and Categories: a computational perspective on constructivism
Research talk at Psychologists, Engineers, and Neuroscientists seminar, Northeastern University, Boston MA, USA
Teaching
Work experience
- Winter 2018: Graduate Visiting Scholar
- Northeastern University
- Development of analyses for fMRI data of the brain
- Adviser: Jan-Willem Van de Meent
- Spring 2017 to Fall 2017: Software Engineer (Full Stack)
- Adept Mobile
- Full-stack Ruby on Rails engineer, from the model to the front-end styling and scripting. Developed the backend to various JSON APIs for feeding data to mobile applications, a loyalty platform for sports teams, and the ecommerce website for the New England Patriots. All applications were run on Heroku and developed with Github.
- Supervisor: Craig Heneveld
- Spring 2015 to Winter 2017: Member of Technical Staff
- LeafLabs, LLC
- Project-based research and development. Developed module firmware, including a boot-ROM, for Google’s Project Ara. Designed the Greybus Bootrom Protocol now deployed in Greybus devices as part of the Motorola Moto-Z. Implemented the Trusted Administration Framework, a series of diskless Linux images built on NixOS for secure cryptographic computations.
- Supervisor: Marti Bolivar
- Fall 2012 to Spring 2015: Graduate Research Assistant
- Technion Israel Institute of Technology
- Thesis “Unstructured Jumps and Compressed Size as Defect-Prediction Metrics”, defended March 2015
- Committee: Yossi Gil and Eran Yahav
Skills
- Bayesian machine learning
- Deep probabilistic programming
- Deep learning
- Functional programming
- Academic writing
- Embedded firmware and embedded Linux development