Risk Phase Transition in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting Oral HILD Workshop ICML 2025
Jipining Li, Rishi Sonthalia
[Workshop Version]
Supermodular Rank: Set Function Decomposition and Optimization. SIAM Journal on Mathematics of Data Science 2025
Rishi Sonthalia, Anna Seigal, and Guido Montufar
[Preprint]
Training Data Induced Double Descent and the Role of Training Noise Level. Transactions of Machine Learning Research. 2023
Rishi Sonthalia, Raj Rao Nadakuditi
[code][paper]
Project and Forget: Solving Large Scale Metric Constrained Problems. Journal of Machine Learning Research. 2022
Rishi Sonthalia, Anna Gilbert
[Code][Arxiv version]{Youtube Video]
Tree! I am no Tree! I am a Low Dimensional Hyperbolic Embedding. Neural Information Processing Symposium (NeurIPS) 2020
Rishi Sonthalia, Anna Gilbert
[Code][paper]
Low Rank Gradients and Where to Find Them. 2025
Rishi Sonthalia, Michael Murray, Guido Montufar
[Workshop Version]
Risk Phase Transition in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting 2025
Jipining Li, Rishi Sonthalia
[Workshop Version]
On Regularization via Early Stopping for Least Squares Regression. 2025
Rishi Sonthalia, Jackie Lok, Elizaveta Rebrova.
[Preprint]
Effect of Geometry on Graph Neural Networks. 2025
Xinyue Li, Praveen Bandhla, and Rishi Sonthalia
[Preprint]
Spectral Neural Networks: Approximation Theory and Optimization Landscape. 2024
Chenghui Li, Rishi Sonthalia, and Nicolas Garcia-Trillos
[Preprint]
Supermodular Rank: Set Function Decomposition and Optimization. SIAM Journal on Mathematics of Data Science 2025
Rishi Sonthalia, Anna Seigal, and Guido Montufar
[Preprint]
Generalization Error without Independence: Denoising, Linear Regression, and Transfer Learning. Transactions of Machine Learning Research. 2024
Chinmaya Kausik, Kashvi Srivastava, and Rishi Sonthalia
[ArXiv Version]
Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network. Nature Machine Intelligence. 2023
Mario Kreen, Lorenzo Buffoni, Bruno Coutinho, Sagi Eppel, Jacob Foster, Andrew Gritsevskiy, Harlin Lee, Yichao Lu, Joa Moutinho, Nima Sanjabi, Rishi Sonthalia, Ngoc Mai Tran, Francisco Valente, Yangxinyu Xie, Rose Yu, Michael Kopp. (Besides the first and last author, the rest are alphabetical)
[code][Arxiv version]
Training Data Induced Double Descent and the Role of Training Noise Level. Transactions of Machine Learning Research. 2023
Rishi Sonthalia and Raj Rao Nadakuditi
[code][paper]
Project and Forget: Solving Large Scale Metric Constrained Problems. Journal of Machine Learning Research. 2022
Rishi Sonthalia and Anna Gilbert
[Code][Arxiv version]{Youtube Video]
Universal Approximation of Mean-Field Models via Transformers. International Conference on Machine Learning (ICML) 2025
Shiba Biswal, Karthik Elamvazhuthi, Rishi Sonthalia
[Paper]
Discrete Error Dynamics of Mini-batch Gradient Descent for Least Squares Regression. Algorithmic Learning Theory (ALT) 2025
Jackie Lok, Rishi Sonthalia, Eizaveta Rebrova
[Preprint]
Least Squares Regression Can Exhibit Under-Parameterized Double Descent. Neural Information Processing Symposium (NeurIPS) 2024
Xinyue Li, Rishi Sonthalia
[Paper]
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization. AISTATS Conference 2024
Yutong Wang, Rishi Sonthalia, Wei Hu
[paper]
How can classical multidimensional scaling go wrong? Neural Information Processing Symposium (NeurIPS) 2021
Rishi Sonthalia, Gregory Van Buskirk, Benjamin Raichel, and Anna Gilbert
[Code][paper]
Tree! I am no Tree! I am a Low Dimensional Hyperbolic Embedding. Neural Information Processing Symposium (NeurIPS) 2020
Rishi Sonthalia and Anna Gilbert
[Code][paper]
Generalized Metric Repair on Graphs. 17th Scandinavian Symposium and Workshops on Algorithm Theory (SWAT) 2020
Fan Chengling, Anna Gilbert, Ben Raichel, Rishi Sonthalia, Greg Van Buskirk (Alphabetical ordering)
[paper]
Unsupervised Metric Learning in Presence of Missing Data. 56th Annual Allerton Conference on Communication, Control, and Computing (Allerton) 2018
Rishi Sonthalia and Anna Gilbert
[Code][paper]
RelWire: Metric Based Graph Rewiring. NeurIPS Workshop on Symmetry and Geometry in Neural Representations 2024
Rishi Sonthalia, Anna Gilbert, and Matthew Durham
[paper]
CubeRep: Learning Relations Between Different Views of Data. Proceedings of Machine Learning Research Volume: Topological, Algebraic, and Geometric Learning. 2022
Rishi Sonthalia, Anna Gilbert, Matthew Durham
[paper]
ICLR 2022 Challenge for Computational Geometry and Topology. Proceedings of Machine Learning Research Volume: Topological, Algebraic, and Geometric Learning. 2022
Adele Myers, Saiteja Utpala, Shubham Talbar, Sophia Sanborn, Christian Shewmake, Claire Donnat, Johan Mathe, Rishi Sonthalia, Xinyue Cui, Tom Szwagier, Arthur Pignet, Andri Bergsson, S\oren Hauberg, Dmitriy Nielsen, Stefan Sommer, David Klindt, Erik Hermansen, Melvin Vaupel, Benjamin Dunn, Jeffrey Xiong, Noga Aharony, Itsik Pe’er, Felix Ambellan, Martin Hanik, Esfandiar Nava-Yazdani, Christoph von Tycowicz, Nina Miolane.
[Code][paper]
Knowledge Graphs of the QAnon Twitter Network. IEEE BigData Conference 2022.
Clay Adams, Malvina Bohzidarova, James Chen, Andrew Gao, Zhengtong Liu, Hunter Priniski, Junyuan Lin, Rishi Sonthalia, Andrea Bertozzi, and Jeffrey Brantingham
[Code][paper]
Hyperbolic and Mixed Geometry Neural Networks. NeurIPS Workshop on Symmetry and Geometry in Neural Representations. 2022
Xinyue Cui and Rishi Sonthalia
[paper]
Dynamic Embedding-based Methods for Link Prediction in Machine Learning Semantic Network IEEE BigData Conference 2021.
Harlin Lee, Rishi Sonthalia, and Jacob Foster
[code][paper]
An Analysis of COVID-19 Knowledge Graphs Construction and Applications. IEEE BigData Conference 2021.
Dominic Flocco, Bryce Palmer-Toy, Ruixiao Wang, Hongyu Zhu, Rishi Sonthalia, Junyuan Lin, Andrea L Bertozzi, P Jeffrey Brantingham
[Code][paper]