Publications
The papers are organized under various different categories of interest. The same paper may appear in multiple categories.
Select First Author Papers
Supermodular Rank: Set Function Decomposition and Optimization. 2023 Preprint
RelWire: Metric Based Graph Rewiring. 2023
Training Data Induced Double Descent and the Role of Training Noise Level. Transactions of Machine Learning Research. 2023
Project and Forget: Solving Large Scale Metric Constrained Problems. Journal of Machine Learning Research. 2022
[Code][Arxiv version]{Youtube Video]
Tree! I am no Tree! I am a Low Dimensional Hyperbolic Embedding. Neural Information Processing Symposium (NeurIPS) 2020
[Code][paper]
Paper Type
Preprints
Discrete Error Dynamics of Mini-batch Gradient Descent for Least Squares Regression. 2024
On Regularization via Early Stopping for Least Squares Regression. 2024
Supermodular Rank: Set Function Decomposition and Optimization. 2023
Under-Parameterized Double Descent for Ridge Regularized Least Squares Denoising. 2023
RelWire: Metric Based Graph Rewiring. 2023
Effect of Geometry on Graph Neural Networks. 2023
Spectral Neural Networks: Approximation Theory and Optimization Landscape. 2023
Journal Publications
Generalization Error without Independence: Denoising, Linear Regression, and Transfer Learning. Transcations of Machine Learning Research. 2024
Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network. Nature Machine Intelligence. 2023
Training Data Induced Double Descent and the Role of Training Noise Level. Transactions of Machine Learning Research. 2023
Project and Forget: Solving Large Scale Metric Constrained Problems. Journal of Machine Learning Research. 2022
[Code][Arxiv version]{Youtube Video]
Conference and Proceedings Papers
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization. AISTATS Conference 2024
Knowledge Graphs of the QAnon Twitter Network. IEEE BigData Conference 2022.
CubeRep: Learning Relations Between Different Views of Data. Proceedings of Machine Learning Research Volume: Topological, Algebraic, and Geometric Learning. 2022
ICLR 2022 Challenge for Computational Geometry and Topology. Proceedings of Machine Learning Research Volume: Topological, Algebraic, and Geometric Learning. 2022
Dynamic Embedding-based Methods for Link Prediction in Machine Learning Semantic Network 2021. IEEE BigData Conference 2021
An Analysis of COVID-19 Knowledge Graphs Construction and Applications. IEEE BigData Conference 2021.
How can classical multidimensional scaling go wrong? Neural Information Processing Symposium (NeurIPS) 2021
Tree! I am no Tree! I am a Low Dimensional Hyperbolic Embedding. Neural Information Processing Symposium (NeurIPS) 2020
[Code][paper]
Generalized Metric Repair on Graphs. 17th Scandinavian Symposium and Workshops on Algorithm Theory (SWAT) 2020
Unsupervised Metric Learning in Presence of Missing Data. 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton) 2018
[Code][paper]
Peer-Reviewed Workshop Papers
Spectral Neural Networks: Approximation Theory and Optimization Landscape. High-dimensional Learning Dynamics 2024: The Emergence of Structure and Reasoning at ICML. 2024
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization. Math for Machine Learning Workshop at NeurIPS 2023
Generalization Error without Independence: Denoising, Linear Regression, and Transfer Learning. Math for Machine Learning Workshop at NeurIPS 2023
RelWire: Metric Based Graph Rewiring. NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations. 2023
Under-Parameterized Double Descent for Ridge Regularized Least Squares Denoising. Math for Machine Learning Workshop at NeurIPS 2023
Hyperbolic and Mixed Geometry Neural Networks. NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations. 2022
Dual Regularized Optimal Transport. Optimal Transport and Machine Learning Workshop at Neural Information Processing Symposium. 2021
Works where I mentor students
Generalization Error without Independence: Denoising, Linear Regression, and Transfer Learning. 2023
Under-Parameterized Double Descent for Ridge Regularized Least Squares Denoising. 2023
Effect of Geometry on Graph Neural Networks. 2023
Knowledge Graphs of the QAnon Twitter Network. IEEE BigData Conference 2022.
Hyperbolic and Mixed Geometry Neural Networks. NeurIPS 2022 Workshop on Symmetry and Geometry in Neural Representations. 2022
An Analysis of COVID-19 Knowledge Graphs Construction and Applications. IEEE BigData Conference 2021.
Other Projects
DeepGreek: Reconstructing Greek Text 2020
[Colab Notebook]