Scholar
Kamil Ciosek
Google Scholar ID: xaOPd1YAAAAJ
Spotify
Citations & Impact
Citations
1,275
H-index
17
i10-index
22
Publications
20
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- - Linear Gradient Prediction with Control Variates
- - Observation Noise and Initialization in Wide Neural Networks
- - Impatient Bandits: Optimizing for the Long-Term Without Delay (journal version)
- - Hallucination Detection on a Budget: Efficient Bayesian Estimation of Semantic Entropy
- - On the Importance of Uncertainty in Decision-Making with Large Language Models
- - Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay
- - Automatic Music Playlist Generation via Simulation-based Reinforcement Learning
- - Imitation Learning by Reinforcement Learning
- - Information Directed Reward Learning for Reinforcement Learning
- - Regularized Policies are Reward Robust
Research Experience
- Works as a Machine Learning Researcher.
Background
- A machine learning generalist, with a focus on Reinforcement Learning, Bayesian Modelling, and Large Language Models. Also interested in the theory of deep learning, particularly the links to Bayesian inference from the angle of the Neural Tangent Kernel. While maintaining an ongoing interest in the fundamentals, applies research to recommendation problems.
Co-authors