Conformal Prediction Sets Can Cause Disparate Impact
Jesse C. Cresswell, Bhargava Kumar, Yi Sui, and Mouloud Belbahri. Conformal Prediction Sets Can Cause Disparate Impact. arXiv preprint 2410.01888
CV
Experience
- 2019 - Present: Sr. Machine Learning Scientist, Layer 6 AI at TD
- Team Lead for Risk applied work
- Team Lead for privacy research
Education
- Ph.D in Theoretical Physics, University of Toronto, 2019
- M.Sc. in Physics, University of Toronto, 2015
- H.B.Sc. in Physics, University of British Columbia, 2014
- Exchange Program - National University of Singapore, 2013
Skills
- Languages: Python, Java, Scala
- Deep Learning Libraries: Pytorch, JAX, Tensorflow
- Frameworks: Azure, Kubernetes, Databricks, Spark, Hadoop
- Data Science Libraries: Scikit-learn, Pandas, Numpy, Scipy
- Scientific Languages: Mathematica, Maple, Matlab
Publications
A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
Hamidreza Kamkari, Brendan Leigh Ross, Rasa Hosseinzadeh, Jesse C. Cresswell, Gabriel Loaiza-Ganem. A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models. In Advances in Neural Information Processing Systems, volume 37, 2024
Benchmarking Robust Self-Supervised Learning Across Diverse Downstream Tasks
Antoni Kowalczuk, Jan Dubiński, Atiyeh Ashari Ghomi, Yi Sui, George Stein, Jiapeng Wu, Jesse C. Cresswell, Franziska Boenisch, Adam Dziedzic. Robust Self-Supervised Learning Across Diverse Downstream Tasks. ICML 2024 Workshop on Foundation Models in the Wild
Scaling Up Diffusion and Flow-based XGBoost Models
Jesse C. Cresswell, Taewoo Kim. Scaling Up Diffusion and Flow-based XGBoost Models. ICML 2024 Workshop on AI for Science
A Geometric Framework for Understanding Memorization in Generative Models
Brendan Leigh Ross, Hamidreza Kamkari, Zhaoyan Liu, Tongzi Wu, George Stein, Gabriel Loaiza-Ganem, Jesse C. Cresswell. A Geometric Framework for Understanding Memorization in Generative Models. ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling
Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections
Gabriel Loaiza-Ganem, Brendan Leigh Ross, Rasa Hosseinzadeh, Anthony L. Caterini, esse C. Cresswell. Deep Generative Models through the Lens of the Manifold Hypothesis: A Survey and New Connections. TMLR 2024
A Geometric Explanation of the Likelihood OOD Detection Paradox
Hamidreza Kamkari, Brendan Leigh Ross, Jesse C. Cresswell, Anthony L. Caterini, Rahul G. Krishnan, Gabriel Loaiza-Ganem. A Geometric Explanation of the Likelihood OOD Detection Paradox. International Conference on Machine Learning 2024
Conformal Prediction Sets Improve Human Decision Making
Jesse C. Cresswell, Yi Sui, Bhargava Kumar, and Noël Vouitsis. Conformal Prediction Sets Improve Human Decision Making. International Conference on Machine Learning 2024
Augment then Smooth: Reconciling Differential Privacy with Certified Robustness
Jiapeng Wu, Atiyeh Ashari Ghomi, David Glukhov, Jesse C. Cresswell, Franziska Boenisch, and Nicholas Papernot. Augment then Smooth: Reconciling Differential Privacy with Certified Robustness. TMLR 2024
Data-Efficient Multimodal Fusion on a Single GPU
Noël Vouitsis, Zhaoyan Liu, Satya Krishna Gorti, Valentin Villecroze, Jesse C. Cresswell, Guangwei Yu, Gabriel Loaiza-Ganem, and Maksims Volkovs. Data-Efficient Multimodal Fusion on a Single GPU. Computer Vision and Pattern Recognition Conference 2024
Self-supervised Representation Learning from Random Data Projectors
Yi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu, George Stein, Xiao Shi Huang, Xiaochen Zhang, Maksims Volkovs. Self-supervised Representation Learning from Random Data Projectors. International Conference on Learning Representations 2024
Neural Implicit Manifold Learning for Topology-Aware Generative Modelling
Brendan Leigh Ross, Gabriel Loaiza-Ganem, Anthony L. Caterini, and Jesse C. Cresswell. Neural Implicit Manifold Learning for Topology-Aware Generative Modelling. TMLR 2024
Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models
George Stein, Jesse C. Cresswell, Rasa Hosseingzadeh, Yi Sui, Brendan Leigh Ross, Valentin Villecroze, Anthony L. Caterini, J. Eric T. Taylor, Gabriel Loaiza-Ganem. Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models. In Advances in Neural Information Processing Systems, volume 36, 2023
Decentralized Federated Learning through Proxy Model Sharing
Shivam Kalra, Junfeng Wen, Jesse C. Cresswell, Maksims Volkovs, and Hamid R. Tizhoosh. Decentralized federated learning through proxy model sharing. Nature Communications 14, 2899, 2023.
Verifying the Union of Manifolds Hypothesis for Image Data
Bradley C.A. Brown, Anthony L. Caterini, Brendan Leigh Ross, Jesse C. Cresswell, and Gabriel Loaiza-Ganem. Verifying the Union of Manifolds Hypothesis for Image Data. International Conference on Learning Representations 2023.
Disparate Impact in Differential Privacy from Gradient Misalignment
Maria S. Esipova, Atiyeh Ashari Ghomi, Yaqiao Luo, and Jesse C. Cresswell. Disparate Impact in Differential Privacy from Gradient Misalignment. International Conference on Learning Representations 2023
Denoising Deep Generative Models
Gabriel Loaiza-Ganem, Brendan Leigh Ross, Luhuan Wu, John P. Cunningham, Jesse C. Cresswell, and Anthony L. Caterini. Denoising Deep Generative Models. NeurIPS 2022 Workshop on Understanding Deep Learning Through Empirical Falsification.
CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
Jesse C. Cresswell, Brendan Leigh Ross, Gabriel Loaiza-Ganem, Humberto Reyes-Gonzalez, Marco Letizia, and Anthony L. Caterini. CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds. NeurIPS 2022 Workshop on Machine Learning and the Physical Sciences.
Find Your Friends: Personalized Federated Learning with the Right Collaborators
Yi Sui, Junfeng Wen, Yenson Lau, Brendan Leigh Ross, and Jesse C. Cresswell. Find Your Friends: Personalized Federated Learning with the Right Collaborators. NeurIPS 2022 Workshop on Federated Learning: Recent Advances and New Challanges
Diagnosing and Fixing Manifold Overfitting in Deep Generative Models
Gabriel Loaiza-Ganem, Brendan Leigh Ross, Jesse C. Cresswell, and Anthony L. Caterini. Diagnosing and Fixing Manifold Overfitting in Deep Generative Models. TMLR 2022
Federated Learning and Differential Privacy for Medical Image Analysis
Mohammed Adnan, Shivam Kalra, Jesse C. Cresswell, Graham W. Taylor, and Hamid R. Tizhoosh. Federated Learning and Differential Privacy for Medical Image Analysis. Nature Scientific Reports, 12, 1953, 2022
Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows
Brendan Leigh Ross and Jesse C. Cresswell. Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows. In Advances in Neural Information Processing Systems, volume 34, 2021
C-Learning: Horizon-Aware Cumulative Accessibility Estimation
Panteha Naderian, Gabriel Loaiza-Ganem, Harry J. Braviner, Anthony L. Caterini, Jesse C. Cresswell, Tong Li, Animesh Garg. C-Learning: Horizon-Aware Cumulative Accessibility Estimation. International Conference on Learning Representations
Operational symmetries of entangled states
Ilan Tzitrin, Aaron Z. Goldberg, and Jesse C. Cresswell, Operational symmetries of entangled states. J. Phys. A: Math. Theor. 53 095304, 2021
Quantum Information Approaches to Quantum Gravity
Jesse C. Cresswell, Quantum Information Approaches to Quantum Gravity. University of Toronto Doctoral Thesis
Holographic relations for OPE blocks in excited states
Jesse C. Cresswell, Ian T. Jardine, and Amanda W. Peet. Holographic relations for OPE blocks in excited states. JHEP 2019 3, 58
Perturbative expansion of entanglement negativity using patterned matrix calculus
Jesse C. Cresswell, Ilan Tzitrin, and Aaron Z. Goldberg. Perturbative expansion of entanglement negativity using patterned matrix calculus. Phys. Rev. A 99 012322, 2019
Universal entanglement timescale for Rényi entropies
Jesse C. Cresswell. Universal entanglement timescale for Rényi entropies. Phys. Rev. A 97 022317, 2018
Kinematic space for conical defects
Jesse C. Cresswell, Amanda W. Peet. Kinematic space for conical defects. JHEP 11 (2017) 155
Lorenz gauge quantization in conformally flat spacetimes
Jesse C. Cresswell and Dan N. Vollick. Lorenz gauge quantization in conformally flat spacetimes. Phys. Rev. D 91, 084008, 2015
Talks
AI in Risk and Compliance: What is Here, What is Coming and What May Never Be!
Talk at ABA Risk and Compliance Conference, Seattle, USA
Uncertainty Quantification through Conformal Prediction
Talk at Roche Knowledge Sharing Workshop, Toronto, Ontario, Canada
Finance x Data Science Panel - Future FinDS
Talk at Students in Data Science and Statistics Union, University of Toronto, Toronto, Ontario, Canada
Generative ML for EHEP and Applications to Calorimeter Shower Simulation
Talk at University of Toronto, Toronto, Ontario, Canada
Quantifying Uncertainty in Model Predictions
Talk at Toronto Machine Learning Summit, Toronto, Ontario, Canada
Disparate Impact in Differential Privacy from Gradient Misalignment
Talk at NeurIPS 2022 Workshop on Algorithmic Fairness through the Lens of Causality and Privacy, New Orleans, Louisiana, USA
Navigating the Tradeoff Between Privacy and Fairness in ML
Talk at Toronto Machine Learning Summit, Toronto, Ontario, Canada
CaloMan: Fast generation of calorimeter showers with density estimation on learned manifolds
Talk at ML4Jets, New Brunswick, New Jersey, USA
Privacy Enhancing Technologies in the Financial Industry: Federated Learning
Talk at Big Data & AI Conference, Toronto, Ontario, Canada
Privacy Enhancing Technologies for Gigapixel Medical Image Analysis
Talk at Machine Learning Research Group, University of Guelph, Guelph, Ontario, Canada
Privacy Enhancing Technologies for Gigapixel Medical Image Analysis
Talk at Endless Summer School: Healthcare Roundup, Vector Institute, Toronto, Ontario, Canada
Protecting Privacy in ML: Introduction to Differential Privacy
Talk at Big Data & AI Conference, Toronto, Ontario, Canada
Protecting Privacy in ML: Introduction to Differential Privacy
Talk at Visitor Speaker Series, Vector Institute, Toronto, Ontario, Canada
Evaluating Model Performance on Highly Imbalanced Datasets
Talk at Data Science Speaker Series, Canadian Statistical Sciences Institute, University of Toronto, Toronto, Ontario, Canada
Holographic relations for OPE blocks in excited states
Talk at It From Qubit Workshop 2019, Kyoto University, Kyoto, Japan
Holographic relations for OPE blocks in AdS3 quotients
Talk at Prospects in Theoretical Physics 2018, Institute for Advanced Study, Princeton, New Jersey, USA
Holographic relations for OPE blocks from kinematic space
Talk at USU Strings and Black Holes Workshop, Utah State University, Logan, Utah, USA
Diffeomorphism invariant holographic dictionary for conical defects
Talk at Seoul National University, Seoul, South Korea
Kinematic Space for Conical Defects
Talk at Strings 2017, Tel Aviv, Israel
Awards
- 2017 - Vanier Canada Graduate Scholarship - U.Toronto
- 2017 - NSERC CGS-Doctoral - U.Toronto
- 2017, 2019 - Van Kranendonk Teaching Assistant Award - U.Toronto
- 2016 - Ontario Graduate Scholarship - U.Toronto
- 2015 - NSERC CGS-Masters - U.Toronto
- 2014 - Distinguished Graduate in Physics - UBC
Service and leadership
- 2018-2019 - Academic Don, University of Trinity College, U.Toronto
- 2016-2019 - Graduate Education Council, School of Graduate Studies, U.Toronto