About

I am currently a 1^st year Computer Science PhD student at University of California Los Angeles, advised by professor Guy Van den Broeck. My research interests include:

Probabilistic Reasoning and Learning
Tractable Probabilistic Models
Explainability and Fairness in AI & ML
Artificial Intelligence
Machine Learning

Pasha Khosravi

UCLA - Computer Science Department
Engineering VI Room 368A
404 Westwood Plaza
Los Angeles, CA 90095-1596

Publications

Conferences

[NeurIPS19]	Pasha Khosravi, YooJung Choi, Yitao Liang, Antonio Vergari and Guy Van den Broeck. On Tractable Computation of Expected Predictions. To appear in NeurIPS, 2019.	Links Paper BibTeX
[IJCAI19]	Pasha Khosravi, Yitao Liang, YooJung Choi, Guy Van den Broeck. What to Expect of Classifiers? Reasoning about Logistic Regression with Missing Features. Published at IJCAI, 2019.	Links Paper BibTeX Poster Slides

Experience

Industry

	Software Engineering Intern, Facebook Ads Delivery Infastructure	June 2018 - Sep 2018
	Sr. Developer, InfiniGlobe Software development on LAMP Stack	Oct 2017 - June 2018
	Software Engineering Intern, Amazon Aws Lex	June 2017 - Sep 2017
	Technical Consultant, Kiersted Systems	June 2015 - Sep 2016

Research

	Graduate Student Researcher Member of Statistical and Relational Artificial Intelligence Lab (StarAI).	Prof. Guy Van den Broeck Sep 2018 - Now
	Undergraduate Research Worked on explaining actions of Reinforcement Learning agents using black-box approaches such as LIME	Prof. Sameer Singh Aug 2017 - June 2018
	Undergraduate Research Worked on algorithm for finding best alignments between multiple biological networks such as Protein-to-Protein networks.	Prof. Wayne Hayes Jan 2016 - June 2018

Teaching

	ICPC Coach Prepared material for the ACM Class, the goal of the class was to improve students' problem solving, coding skills, and preparing them for competitions like ACM ICPC.	ACM @ UCI Sep 2017 - June 2018
	Math Tutor Tutored all lower division math classes including calculus, Linear Algebra, Differential Equations, and Discrete Math	Irvine Valley College Aug 2014 – May 2015

Projects

	Naive Conformant Learning (NaCL) Given a logistic regression (LR) model, NaCL learns a Naive Bayes model that conforms to the LR model while maximizing the joint feature likelihood on the dataset. The learned model gives us the ability to handle missing features, while getting benefits of higher accuracy of LR models. Code:
	Zombie Hunter Used reinforcement learning and deep learning to build a agent to learn to fight zombies in Minecraft (Malmo platform) Project in AI Class (CS 175, Spring 2017, UC Irvine) Project Report Website Thought by Professor Sameer Singh
	Amadeus Explored different neural network architectures for detecting music genre only using raw music. Deep Learning & Neural Networks (CS 172B, Winter 2018, UC Irvine) Thought by Professor Pierre Baldi.

Awards/Honors

	Ranked 56^th in ACM ICPC World Finals, May 2017 Ranked 1^st in ACM ICPC Soutern California Regional, Nov 2016 Ranked 3^rd in ACM ICPC Soutern California Regional, Nov 2017
	Ranked 59^th in IEEExtreme 10.0, Oct 2016 (1^st in USA) Ranked 24^th in IEEExtreme 11.0, Oct 2017 (2^nd in USA)

Education

I got my Bachelor's degree in Computer Science from University of California Irvine speciallizing in Intelligent Systems. Before that I finished UC's Transfer Curriculum at Irvine Valley College, also briefly attended Sharif University of Technology.

CS PhD

2018 - 2023

CS BS

2015 - 2018

AA

2013 - 2015

CS

2012 - 2013