AI in Risk and Compliance: What is Here, What is Coming and What May Never Be!
Talk, ABA Risk and Compliance Conference, Seattle, USA
[Website]
Talks and presentations
Uncertainty Quantification through Conformal Prediction
Talk, Roche Knowledge Sharing Workshop, Toronto, Ontario, Canada
Finance x Data Science Panel - Future FinDS
Talk, Students in Data Science and Statistics Union, University of Toronto, Toronto, Ontario, Canada
[Website]Generative ML for EHEP and Applications to Calorimeter Shower Simulation
Talk, University of Toronto, Toronto, Ontario, Canada
[Website]Quantifying Uncertainty in Model Predictions
Talk, Toronto Machine Learning Summit, Toronto, Ontario, Canada
[Video] [Slides]Disparate Impact in Differential Privacy from Gradient Misalignment
Talk, NeurIPS 2022 Workshop on Algorithmic Fairness through the Lens of Causality and Privacy, New Orleans, Louisiana, USA
[Video] [Slides] [Website]Navigating the Tradeoff Between Privacy and Fairness in ML
Talk, Toronto Machine Learning Summit, Toronto, Ontario, Canada
[Video] [Slides]CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
Talk, ML4Jets, New Brunswick, New Jersey, USA
[Slides] [Website]Privacy Enhancing Technologies in the Financial Industry: Federated Learning
Talk, Big Data & AI Conference, Toronto, Ontario, Canada
[Video] [Slides]Privacy Enhancing Technologies for Gigapixel Medical Image Analysis
Talk, Machine Learning Research Group, University of Guelph, Guelph, Ontario, Canada
Due to the sensitive nature of medical data, hospitals are unable to merge their datasets to develop models. Our work indicates that differentially private federated learning is a viable and reliable framework for the collaborative development of machine learning models in medical image analysis.
Privacy Enhancing Technologies for Gigapixel Medical Image Analysis
Talk, Endless Summer School: Healthcare Roundup, Vector Institute, Toronto, Ontario, Canada
[Slides]Protecting Privacy in ML: Introduction to Differential Privacy
Talk, Big Data & AI Conference, Toronto, Ontario, Canada
[Slides]Protecting Privacy in ML: Introduction to Differential Privacy
Talk, Visitor Speaker Series, Vector Institute, Toronto, Ontario, Canada
[Video] [Slides]Evaluating Model Performance on Highly Imbalanced Datasets
Talk, Data Science Speaker Series, Canadian Statistical Sciences Institute, University of Toronto, Toronto, Ontario, Canada
[Website]Holographic relations for OPE blocks in excited states
Talk, It From Qubit Workshop 2019, Kyoto University, Kyoto, Japan
Holographic relations for OPE blocks in AdS3 quotients
Talk, Prospects in Theoretical Physics 2018, Institute for Advanced Study, Princeton, New Jersey, USA
Holographic relations for OPE blocks from kinematic space
Talk, USU Strings and Black Holes Workshop, Utah State University, Logan, Utah, USA
Diffeomorphism invariant holographic dictionary for conical defects
Talk, Seoul National University, Seoul, South Korea
Kinematic Space for Conical Defects
Talk, Strings 2017, Tel Aviv, Israel