1 citations · 1 across the 4 of their papers we have counts for
6 papers
Generalization in Neural Networks Through the Lens of Magnitude Potential
Sahel Torkamani, Henry Gouk, Rik Sarkar
Explaining generalization and training dynamics in neural networks remains a challenge, and various approaches have been developed to study different aspects of these phenomena. In…
Magnitude Distance: A Geometric Measure of Dataset Similarity
Sahel Torkamani, Henry Gouk, Rik Sarkar
Quantifying the distance between datasets is a fundamental question in mathematics and machine learning. We propose \textit{magnitude distance}, a novel distance metric defined on…
PrivaDE: Privacy-preserving Data Evaluation for Blockchain-based Data Marketplaces
Wan Ki Wong, Sahel Torkamani, Michele Ciampi +1
Evaluating the usefulness of data before purchase is essential when obtaining data for high-quality machine learning models, yet both model builders and data providers are often un…
Count on Your Elders: Laplace vs Gaussian Noise
Joel Daniel Andersson, Rasmus Pagh, Teresa Anna Steiner +1
In recent years, Gaussian noise has become a popular tool in differentially private algorithms, often replacing Laplace noise which dominated the early literature. Gaussian noise i…
Optimal Binary Differential Privacy via Graphs
Sahel Torkamani, Javad B. Ebrahimi, Parastoo Sadeghi +2
We present the notion of \emph{reasonable utility} for binary mechanisms, which applies to all utility functions in the literature. This notion induces a partial ordering on the pe…
Heterogeneous Differential Privacy via Graphs
Sahel Torkamani, Javad B. Ebrahimi, Parastoo Sadeghi +2
We generalize a previous framework for designing utility-optimal differentially private (DP) mechanisms via graphs, where datasets are vertices in the graph and edges represent dat…