Rishi Sonthalia

Boston College — United States

Computer Science · Physical Sciences

5h-index106citations30works0.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Neural Networks and Applications(7), Complex Network Analysis Techniques(5), Face and Expression Recognition(4), Sparse and Compressive Sensing Techniques(4), Complexity and Algorithms in Graphs(4)

Publications30 total

Spectral Neural Networks: Approximation Theory and Optimization Landscape
Journal of Machine Learning·2026Open Access
Supermodular Rank: Set Function Decomposition and Optimization
SIAM Journal on Mathematics of Data Science·2025Open Access
Matricial Free Energy as a Gaussianizing Regularizer: Enhancing Autoencoders for Gaussian Code Generation
arXiv (Cornell University)·2025Open Access
Risk Phase Transitions in Spiked Regression: Alignment Driven Benign and Catastrophic Overfitting
arXiv (Cornell University)·2025Open Access
Low Rank Gradients and Where to Find Them
arXiv (Cornell University)·2025Open Access
Generalization for Least Squares Regression With Simple Spiked Covariances
arXiv (Cornell University)·2024Open Access
Universal Approximation of Mean-Field Models via Transformers
arXiv (Cornell University)·2024· 1 citedOpen Access
Error dynamics of mini-batch gradient descent with random reshuffling for least squares regression
arXiv (Cornell University)·2024Open Access
On Regularization via Early Stopping for Least Squares Regression
arXiv (Cornell University)·2024Open Access
Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization
arXiv (Cornell University)·2024Open Access
Least Squares Regression Can Exhibit Under-Parameterized Double Descent
2024
Forecasting the future of artificial intelligence with machine learning-based link prediction in an exponentially growing knowledge network
Nature Machine Intelligence·2023· 66 citedOpen Access
Spectral Neural Networks: Approximation Theory and Optimization Landscape
arXiv (Cornell University)·2023Open Access
Double Descent and Overfitting under Noisy Inputs and Distribution Shift for Linear Denoisers
arXiv (Cornell University)·2023Open Access
Supermodular Rank: Set Function Decomposition and Optimization
arXiv (Cornell University)·2023Open Access
Least Squares Regression Can Exhibit Under-Parameterized Double Descent
arXiv (Cornell University)·2023· 1 citedOpen Access
Knowledge Graphs of the QAnon Twitter Network
2022 IEEE International Conference on Big Data (Big Data)·2022· 4 cited
Predicting the Future of AI with AI: High-quality link prediction in an exponentially growing knowledge network
arXiv (Cornell University)·2022· 7 citedOpen Access
ICLR 2022 Challenge for Computational Geometry and Topology: Design and Results
arXiv (Cornell University)·2022Open Access
An Analysis of COVID-19 Knowledge Graph Construction and Applications
2021 IEEE International Conference on Big Data (Big Data)·2021· 2 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Anna C. Gilbert(7), Jacob G. Foster(3), Harlin Lee(3), Benjamin Raichel(3), Gregory Van Buskirk(3), Guido Montúfar(3), Mario Krenn(2), Lorenzo Buffoni(2), Bruno Coutinho(2), Sagi Eppel(2), Andrew Gritsevskiy(2), Yichao Lu(2), João P. Moutinho(2), Nima Sanjabi(2), Ngoc Mai Tran(2), Francisco Valente(2), Yangxinyu Xie(2), Rose Yu(2), Michael Kopp(2), Chenglin Fan(2)