Vardan Papyan
Vardan Papyan
Assistant Professor, University of Toronto
Dirección de correo verificada de - Página principal
Citado por
Citado por
Prevalence of neural collapse during the terminal phase of deep learning training
V Papyan, XY Han, DL Donoho
Proceedings of the National Academy of Sciences 117 (40), 24652-24663, 2020
Convolutional neural networks analyzed via convolutional sparse coding
V Papyan, Y Romano, M Elad
Journal of Machine Learning Research 18 (83), 1-52, 2017
Multi-scale patch-based image restoration
V Papyan, M Elad
IEEE Transactions on image processing 25 (1), 249-261, 2015
Neural proximal gradient descent for compressive imaging
M Mardani, Q Sun, D Donoho, V Papyan, H Monajemi, S Vasanawala, ...
Advances in Neural Information Processing Systems 31, 2018
Convolutional dictionary learning via local processing
V Papyan, Y Romano, J Sulam, M Elad
Proceedings of the IEEE International Conference on Computer Vision, 5296-5304, 2017
Working locally thinking globally: Theoretical guarantees for convolutional sparse coding
V Papyan, J Sulam, M Elad
IEEE Transactions on Signal Processing 65 (21), 5687-5701, 2017
Multilayer convolutional sparse modeling: Pursuit and dictionary learning
J Sulam, V Papyan, Y Romano, M Elad
IEEE Transactions on Signal Processing 66 (15), 4090-4104, 2018
Theoretical foundations of deep learning via sparse representations: A multilayer sparse model and its connection to convolutional neural networks
V Papyan, Y Romano, J Sulam, M Elad
IEEE Signal Processing Magazine 35 (4), 72-89, 2018
Neural collapse under mse loss: Proximity to and dynamics on the central path
XY Han, V Papyan, DL Donoho
arXiv preprint arXiv:2106.02073, 2021
The full spectrum of deepnet hessians at scale: Dynamics with sgd training and sample size
V Papyan
arXiv preprint arXiv:1811.07062, 2018
Measurements of three-level hierarchical structure in the outliers in the spectrum of deepnet hessians
V Papyan
arXiv preprint arXiv:1901.08244, 2019
Traces of class/cross-class structure pervade deep learning spectra
V Papyan
Journal of Machine Learning Research 21 (252), 1-64, 2020
Llm censorship: A machine learning challenge or a computer security problem?
D Glukhov, I Shumailov, Y Gal, N Papernot, V Papyan
arXiv preprint arXiv:2307.10719, 2023
Expert surgeons and deep learning models can predict the outcome of surgical hemorrhage from 1 min of video
DJ Pangal, G Kugener, Y Zhu, A Sinha, V Unadkat, DJ Cote, B Strickland, ...
Scientific reports 12 (1), 8137, 2022
Degrees of freedom analysis of unrolled neural networks
M Mardani, Q Sun, V Papyan, S Vasanawala, J Pauly, D Donoho
arXiv preprint arXiv:1906.03742, 2019
Utility of the simulated outcomes following carotid artery laceration video data set for machine learning applications
G Kugener, DJ Pangal, T Cardinal, C Collet, E Lechtholz-Zey, S Lasky, ...
JAMA network open 5 (3), e223177-e223177, 2022
AI and the digitized photoarchive: Promoting access and discoverability
E Prokop, X Han, V Papyan, DL Donoho, CR Johnson Jr
Art Documentation: Journal of the Art Libraries Society of North America 40 …, 2021
Multimodal latent variable analysis
V Papyan, R Talmon
Signal Processing 142, 178-187, 2018
Expert Surgeons and Deep Learning Models Can Predict the Outcome of Surgical Hemorrhage from One Minute of Video
DJ Pangal, G Kugener, Y Zhu, A Sinha, V Unadkat, DJ Cote, B Strickland, ...
medRxiv, 2022.01. 22.22269640, 2022
Out of the ordinary: Spectrally adapting regression for covariate shift
B Eyre, E Creager, D Madras, V Papyan, R Zemel
arXiv preprint arXiv:2312.17463, 2023
El sistema no puede realizar la operación en estos momentos. Inténtalo de nuevo más tarde.
Artículos 1–20