Sepehr Elahi

Student Member | Doctoral Assistant at Ecole Polytechnique Fédérale de Lausanne
Elahi, Sepehr
SPIE Leadership: Retrieving Data, please wait...
SPIE Membership: 2.1 years
SPIE Involvement: Retrieving Data, please wait...
Area of Expertise: Statistical machine learning, Optimization, Bayesian learning, Computer vision
Websites: Personal Website | Personal Website
Social Media: LinkedIn
Contact Details:
Sign In to send a private message or view contact details

Profile Summary

Sepehr is a second-year Doctoral Assistant at the EDIC (Computer and Communication Sciences) department of EPFL. He is advised by Prof. Patrick Thiran of the INDY lab and Prof. Negar Kiyavash of the BAN group. He mainly does research on causal inference & discovery, bandit problems, Bayesian learning, and in general mathematical machine learning. He has also worked on applications of machine learning to computer vision, laser material processing, and other fields.

He graduated with two BSc's summa cum laude from the departments of Electrical & Electronics Engineering and Mathematics from Bilkent University, Ankara, in June of 2022. There, he did research at Bilkent CYBORG and authored papers on online decision making, contextual bandits, Gaussian processes, multi-objective optimization, and their applications to crowdsourcing/sensing, content recommendation, and item recommendation. Additionally, Sepehr has authored works and is interested in applications of machine learning to various fields including laser material processing, computer vision and image processing, telecommunications, and microfluidic droplet generation.

Upcoming Presentations

Most Recent | Show All
Retrieving Data, please wait...


Most Recent | Show All
Retrieving Data, please wait...

Conference Committee Involvement

Most Recent | Show All
Retrieving Data, please wait...

Course Instructor

Most Recent | Show All
Retrieving Data, please wait...
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research