Sina Ghiassian

Researcher, Spotify

Joined

May 2020

Names

Sina Ghiassian (Preferred)

Emails

****@ualberta.ca (Confirmed)

****@spotify.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

Spotify (spotify.com)

2022 – Present

PhD student

University of Alberta (ualberta.ca)

2015 – 2022

MS student

University of Alberta (ualberta.ca)

2012 – 2014

Advisors, Relations & Conflicts

PhD Advisor

Adam White

2018 – Present

PhD Advisor

Richard Sutton

2015 – Present

MSc Advisor

Russell Greiner

2012 – 2014

Expertise

Reinforcement Learning

2015 – Present

Artificial Intelligence

2012 – Present

Supervised Learning

2012 – 2014

Publications

Measuring Uncertainty Calibration
Kamil Ciosek, Nicolò Felicioni, Sina Ghiassian, Juan Elenter, Francesco Tonolini, David Gustafsson, Eva Garcia-Martin, Carmen Barcena Gonzalez, Raphaëlle Bertrand-Lalo
- ICLR 2026 Poster
- Readers: Everyone
Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy
Kamil Ciosek, Nicolò Felicioni, Sina Ghiassian
- Accepted by TMLR
- Readers: Everyone
Learning in complex action spaces without policy gradients
Arash Tavakoli, Sina Ghiassian, Nemanja Rakicevic
- Accepted by TMLR
- Readers: Everyone
Soft Preference Optimization: Aligning Language Models to Expert Distributions
Arsalan Sharifnassab, Saber Salehkaleybar, Sina Ghiassian, Surya Kanoria, Dale Schuurmans
- Submitted to ICLR 2025
- Readers: Everyone
Learning in complex action spaces without policy gradients
Arash Tavakoli, Sina Ghiassian, Nemanja Rakicevic
- Submitted to ICLR 2025
- Readers: Everyone
On the Importance of Uncertainty in Decision-Making with Large Language Models
Nicolò Felicioni, Lucas Maystre, Sina Ghiassian, Kamil Ciosek
- Accepted by TMLR
- Readers: Everyone
In-context Exploration-Exploitation for Reinforcement Learning
Zhenwen Dai, Federico Tomasi, Sina Ghiassian
- ICLR 2024 poster
- Readers: Everyone
Does the Adam Optimizer Exacerbate Catastrophic Forgetting?
Dylan R. Ashley, Sina Ghiassian, Richard S. Sutton
- 30 Sept 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
Auxiliary task discovery through generate and test
Banafsheh Rafiee, Sina Ghiassian, Jun Jin, Richard S. Sutton, Jun Luo, Adam White
- Published: 01 Feb 2023, Last Modified: 13 Feb 2023
- Submitted to ICLR 2023
- Readers: Everyone
Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks.
Sina Ghiassian, Banafsheh Rafiee, Yat Long Lo, Adam White
- 2020 (modified: 09 Nov 2022)
- CoRR2020
- Readers: Everyone

View all 17 publications

Co-Authors

View all 30 co-authors