Zobrazeno 1 - 10
of 691
pro vyhledávání: '"Roberts, Daniel P"'
Autor:
McCloskey, Daniel J., Roberts, Daniel, Rodgers, Lila V. H., Barsukov, Yuri, Kaganovich, Igor D., Simpson, David A., de Leon, Nathalie P., Stacey, Alastair, Dontschuk, Nikolai
Chemical functionalization of diamond surfaces by hydrogen is an important method for controlling the charge state of near-surface fluorescent color centers, an essential process in fabricating devices such as diamond field-effect transistors and che
Externí odkaz:
http://arxiv.org/abs/2406.12249
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
We empirically study a simple layer-pruning strategy for popular families of open-weight pretrained LLMs, finding minimal degradation of performance on different question-answering benchmarks until after a large fraction (up to half) of the layers ar
Externí odkaz:
http://arxiv.org/abs/2403.17887
Nearly a hundred progenitor-less, thin stellar streams have been discovered in the Milky Way, thanks to Gaia and related surveys. Most streams are believed to have formed from star clusters and it was recently proposed that extended star clusters --
Externí odkaz:
http://arxiv.org/abs/2402.06393
A boron-oxide termination of the diamond (100) surface has been formed by depositing molecular boron oxide $\rm{B_2O_3}$ onto the hydrogen-terminated (100) diamond surface under ultrahigh vacuum conditions and annealing to $\rm{950^{\circ} C}$. The r
Externí odkaz:
http://arxiv.org/abs/2402.03940
Fully-connected deep neural networks with weights initialized from independent Gaussian distributions can be tuned to criticality, which prevents the exponential growth or decay of signals propagating through the network. However, such networks still
Externí odkaz:
http://arxiv.org/abs/2310.07765
Large language models with a huge number of parameters, when trained on near internet-sized number of tokens, have been empirically shown to obey neural scaling laws: specifically, their performance behaves predictably as a power law in either parame
Externí odkaz:
http://arxiv.org/abs/2210.16859
Autor:
Upadhyay, Rakesh K., Shao, Jonathan, Maul, Jude E., Schomberg, Harry, Handa, Avtar K., Roberts, Daniel P., Mattoo, Autar K.
Publikováno v:
In Journal of Plant Physiology December 2024 303
Publikováno v:
Cambridge University Press (2022)
This book develops an effective theory approach to understanding deep neural networks of practical relevance. Beginning from a first-principles component-level picture of networks, we explain how to determine an accurate description of the output of
Externí odkaz:
http://arxiv.org/abs/2106.10165
Autor:
Roberts, Daniel A.
We derive a simple and model-independent formula for the change in the generalization gap due to a gradient descent update. We then compare the change in the test error for stochastic gradient descent to the change in test error from an equivalent nu
Externí odkaz:
http://arxiv.org/abs/2104.04874