John K. Feser
I am a PhD student at MIT CSAIL, working with Armando Solar Lezama. I received my Undergraduate and Master's degrees from Rice University, where I worked with Swarat Chaudhuri.
My research interests are in automated program synthesis and program analysis.
Query Optimization for Dynamic Imputation. José Cambronero*, John K. Feser*, Micah J. Smith*, Samuel Madden. VLDB. (2017) To appear. [pdf]
Synthesizing Data Structure Transformations from Input-Output Examples. John K. Feser, Swarat Chaudhuri, Isil Dillig. PLDI. (2015) [pdf]
*Authors contributed equally to this paper.
Inductive Program Synthesis from Input-Output Examples. Master's Thesis. Rice University, Department of Computer Science. Advisors: Swarat Chaudhuri, Christopher Jermaine, Moshe Y. Vardi. (2016) [pdf]
Neural Functional Programming. John K. Feser, Marc Brockschmidt, Alexander L. Gaunt, Daniel Tarlow. arXiv:1611.01988. (2017) [pdf, arXiv]
- Neural Functional Programming. John K. Feser, Marc Brockschmidt, Alexander L. Gaunt, Daniel Tarlow. ICLR. (2017) [pdf]
- Synthesizing Data Structure Transformations from Input-Output Examples John K. Feser, Swarat Chaudhuri, Isil Dillig. PLDI. (2015) [pdf]
- Unification and Partial Evaluation for Component Based Synthesis. John K. Feser, Vijayaraghavan Murali, Swarat Chaudhuri, Isil Dillig. PLDI SRC. (2015) [pdf]
λ2: A tool for synthesizing functional programs from input-output examples. [repository]
ImputeDB: A database with automatic dynamic imputation of missing values. [repository]
Internship at Microsoft Research (Cambridge). Summer 2016. Worked with Marc Brockschmidt and Daniel Tarlow on synthesizing functional programs using machine learning.
Internship at Microsoft Research (Redmond). Summer 2015. Worked with Sumit Gulwani and Rishabh Singh on a program synthesis tool for filtering log files.
Teaching assistant for Comp 382 (Fall 2015), Comp 421 (Spring 2015, Spring 2016) at Rice University.