Philip Greengard

20 papers A* 4Journal 16

Year	Rank	Type	Title / Venue / Authors
2026	A*	`conf`	A Network of Biologically Inspired Rectified Spectral Units (ReSUs) Learns Hierarchical Features Without Error Backpropagation. AAAI Shanshan Qin, Joshua Pughe-Sanford, Alexander Genkin, Pembe Gizem Özdil, Philip Greengard, Anirvan M. Sengupta, Dmitri B. Chklovskii
2025	J	`jnl`	Efficient Fourier Representations of Families of Gaussian Processes. SIAM J. Sci. Comput. Philip Greengard
2025	J	`jnl`	Equispaced Fourier Representations for Efficient Gaussian Process Regression from a Billion Data Points. SIAM/ASA J. Uncertain. Quantification Philip Greengard, Manas Rachh, Alex H. Barnett
2024	A*	`conf`	LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning. ICLR Han Guo, Philip Greengard, Eric P. Xing, Yoon Kim
2024	J	`jnl`	LoRA Learns Less and Forgets Less. CoRR Dan Biderman, Jose Javier Gonzalez Ortiz, Jacob P. Portes, Mansheej Paul, Philip Greengard, Connor Jennings, Daniel King, Sam Havens, Vitaliy Chiley, Jonathan Frankle, Cody Blakeney, John P. Cunningham
2024	J	`jnl`	LoRA Learns Less and Forgets Less. Trans. Mach. Learn. Res. Dan Biderman, Jacob P. Portes, Jose Javier Gonzalez Ortiz, Mansheej Paul, Philip Greengard, Connor Jennings, Daniel King, Sam Havens, Vitaliy Chiley, Jonathan Frankle, Cody Blakeney, John Patrick Cunningham
2023	A*	`conf`	Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach. ICLR Han Guo, Philip Greengard, Hongyi Wang, Andrew Gelman, Yoon Kim, Eric P. Xing
2023	J	`jnl`	Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach. CoRR Han Guo, Philip Greengard, Hongyi Wang, Andrew Gelman, Yoon Kim, Eric P. Xing
2023	J	`jnl`	LQ-LoRA: Low-rank Plus Quantized Matrix Decomposition for Efficient Language Model Finetuning. CoRR Han Guo, Philip Greengard, Eric P. Xing, Yoon Kim
2023	A*	`conf`	Learning to Grow Pretrained Models for Efficient Transformer Training. ICLR Peihao Wang, Rameswar Panda, Lucas Torroba Hennigen, Philip Greengard, Leonid Karlinsky, Rogério Feris, David Daniel Cox, Zhangyang Wang, Yoon Kim
2023	J	`jnl`	Learning to Grow Pretrained Models for Efficient Transformer Training. CoRR Peihao Wang, Rameswar Panda, Lucas Torroba Hennigen, Philip Greengard, Leonid Karlinsky, Rogério Feris, David Daniel Cox, Zhangyang Wang, Yoon Kim
2023	J	`jnl`	Uniform approximation of common Gaussian process kernels using equispaced Fourier grids. CoRR Alex H. Barnett, Philip Greengard, Manas Rachh
2022	J	`jnl`	A fast regression via SVD and marginalization. Comput. Stat. Philip Greengard, Andrew Gelman, Aki Vehtari
2022	J	`jnl`	Efficient reduced-rank methods for Gaussian processes with eigenfunction expansions. Stat. Comput. Philip Greengard, Michael O'Neil
2022	J	`jnl`	Equispaced Fourier representations for efficient Gaussian process regression from a billion data points. CoRR Philip Greengard, Manas Rachh, Alex H. Barnett
2022	J	`jnl`	On a linearization of quadratic Wasserstein distance. CoRR Philip Greengard, Jeremy G. Hoskins, Nicholas F. Marshall, Amit Singer
2021	J	`jnl`	Efficient Fourier representations of families of Gaussian processes. CoRR Philip Greengard
2021	J	`jnl`	Efficient reduced-rank methods for Gaussian processes with eigenfunction expansions. CoRR Philip Greengard, Michael O'Neil
2020	J	`jnl`	A Fast Linear Regression via SVD and Marginalization. CoRR Philip Greengard, Andrew Gelman, Aki Vehtari
2019	J	`jnl`	An algorithm for the evaluation of the incomplete gamma function. Adv. Comput. Math. Philip Greengard, Vladimir Rokhlin