Zobrazeno 1 - 10
of 120
pro vyhledávání: '"Donoho, P. L."'
Autor:
Kazdan, Joshua, Schaeffer, Rylan, Dey, Apratim, Gerstgrasser, Matthias, Rafailov, Rafael, Donoho, David L., Koyejo, Sanmi
The increasing presence of AI-generated content on the internet raises a critical question: What happens when generative machine learning models are pretrained on web-scale datasets containing data created by earlier models? Some authors prophesy \te
Externí odkaz:
http://arxiv.org/abs/2410.16713
Autor:
Gerstgrasser, Matthias, Schaeffer, Rylan, Dey, Apratim, Rafailov, Rafael, Sleight, Henry, Hughes, John, Korbak, Tomasz, Agrawal, Rajashree, Pai, Dhruv, Gromov, Andrey, Roberts, Daniel A., Yang, Diyi, Donoho, David L., Koyejo, Sanmi
The proliferation of generative models, combined with pretraining on web-scale data, raises a timely question: what happens when these models are trained on their own generated outputs? Recent investigations into model-data feedback loops proposed th
Externí odkaz:
http://arxiv.org/abs/2404.01413
Autor:
Donoho, David L., Feldman, Michael J.
Modern datasets are trending towards ever higher dimension. In response, recent theoretical studies of covariance estimation often assume the proportional-growth asymptotic framework, where the sample size $n$ and dimension $p$ are comparable, with $
Externí odkaz:
http://arxiv.org/abs/2210.04488
The recently discovered Neural Collapse (NC) phenomenon occurs pervasively in today's deep net training paradigm of driving cross-entropy (CE) loss towards zero. During NC, last-layer features collapse to their class-means, both classifiers and class
Externí odkaz:
http://arxiv.org/abs/2106.02073
Autor:
Donoho, David L., Kipnis, Alon
Consider a multiple hypothesis testing setting involving rare/weak effects: relatively few tests, out of possibly many, deviate from their null hypothesis behavior. Summarizing the significance of each test by a P-value, we construct a global test ag
Externí odkaz:
http://arxiv.org/abs/2103.03218
Publikováno v:
Annals of Statistics, 2023
We derive a formula for optimal hard thresholding of the singular value decomposition in the presence of correlated additive noise; although it nominally involves unobservables, we show how to apply it even where the noise covariance structure is not
Externí odkaz:
http://arxiv.org/abs/2009.12297
Modern practice for training classification deepnets involves a Terminal Phase of Training (TPT), which begins at the epoch where training error first vanishes; During TPT, the training error stays effectively zero while training loss is pushed towar
Externí odkaz:
http://arxiv.org/abs/2008.08186
Autor:
Donoho, David L., Kipnis, Alon
Publikováno v:
Annals of Statistics 2022, Vol. 50, No. 3, 1447-1472
We adapt Higher Criticism (HC) to the comparison of two frequency tables which may -- or may not -- exhibit moderate differences between the tables in some unknown, relatively small subset out of a large number of categories. Our analysis of the powe
Externí odkaz:
http://arxiv.org/abs/2007.01958
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Monajemi, Hatef, Murri, Riccardo, Jonas, Eric, Liang, Percy, Stodden, Victoria, Donoho, David L.
Modern data science research can involve massive computational experimentation; an ambitious PhD in computational fields may do experiments consuming several million CPU hours. Traditional computing practices, in which researchers use laptops or shar
Externí odkaz:
http://arxiv.org/abs/1901.08705