School of Informatics · University of Edinburgh
Sahel Torkamani
School of Informatics · University of Edinburgh
I am a Ph.D. student in Computer Science at the University of Edinburgh, advised by Professor Rik Sarkar. My research focuses on Differential Privacy and Theoretical Machine Learning.
I completed my B.Sc. in Applied Mathematics at Sharif University of Technology, working with Professor Javad Ebrahimi on Differential Privacy and Information Theory. I also interned at IST Austria with Professor Marco Mondelli on Channel Coding and Machine Learning.
Research Interests
Hover over a project to read more.
Generalization in Neural Networks Through the Lens of Magnitude Potential
Under Review · 2026
The magnitude potential ratio, computed at the logit layer, correlates with Feldman memorization scores, detects decision boundary shifts, and provides a geometric indicator of grokking.
Magnitude Distance: A Geometric Measure of Dataset Similarity
Accepted · ICML 2026
A novel distance metric on finite datasets based on the magnitude of a metric space, with a tunable scale parameter and strong theoretical guarantees.
Privacy Requires Slicing: Differentially Private Magnitude via Projections
EuroTDP 2026
Sliced magnitude (SMag), with global sensitivity bounded uniformly in scale and dimension, enabling ε-differentially private release via the Laplace mechanism.
2024 – 2028 · University of Edinburgh
2019 – 2023 · Sharif University of Technology
2013 – 2019 · NODET
September 2026
Paper accepted at the 1st European Workshop on the Theory of Differential Privacy (EuroTDP 2026), ISTA, Austria.
Event pageMay 2026
Selected as a finalist in the Research Spotlight Competition at the London Hopper Colloquium 2026, hosted by UCL & BCS Academy of Computing.
Event pageMay 2026
Paper accepted at ICML 2026.
ICMLDecember 2025
Attending the Workshop on Principles of Generative Modeling (PriGM) @ EurIPS2025.
OpenReviewClick any photo to explore.
