User profiles for Aaron Mishkin
Aaron MishkinPhD Student, Stanford University Verified email at cs.stanford.edu Cited by 306 |
Painless stochastic gradient: Interpolation, line-search, and convergence rates
Recent works have shown that stochastic gradient descent (SGD) achieves the fast convergence
rates of full-batch gradient descent for over-parameterized models satisfying certain …
rates of full-batch gradient descent for over-parameterized models satisfying certain …
Sex differences in leg vasodilation during graded knee extensor exercise in young adults
…, JA Pelberg, AD Mishkin… - Journal of Applied …, 2007 - journals.physiology.org
Limb vascular conductance responses to pharmacological and nonexercise vasodilator stimuli
are generally augmented in women compared with men. In the present investigation, we …
are generally augmented in women compared with men. In the present investigation, we …
Sex-specific influence of aging on exercising leg blood flow
…, JA Pelberg, AD Mishkin… - Journal of applied …, 2008 - journals.physiology.org
Our previous work suggests that healthy human aging is associated with sex-specific
differences in leg vascular responses during large muscle mass exercise (2-legged cycling) (…
differences in leg vascular responses during large muscle mass exercise (2-legged cycling) (…
Fast convex optimization for two-layer relu networks: Equivalent model classes and cone decompositions
We develop fast algorithms and robust software for convex optimization of two-layer neural
networks with ReLU activation functions. Our work leverages a convex re-formulation of the …
networks with ReLU activation functions. Our work leverages a convex re-formulation of the …
Slang: Fast structured covariance approximations for bayesian deep learning with natural gradient
A Mishkin, F Kunstner, D Nielsen… - Advances in neural …, 2018 - proceedings.neurips.cc
Uncertainty estimation in large deep-learning models is a computationally challenging task,
where it is difficult to form even a Gaussian approximation to the posterior distribution. In …
where it is difficult to form even a Gaussian approximation to the posterior distribution. In …
Letermovir treatment of cytomegalovirus infection or disease in solid organ and hematopoietic cell transplant recipients
…, M Malinis, M Hakki, A Mishkin… - Transplant Infectious …, 2021 - Wiley Online Library
Background Few options are available for cytomegalovirus (CMV) treatment in transplant
recipients resistant, refractory, or intolerant to approved agents. Letermovir (LET) is approved …
recipients resistant, refractory, or intolerant to approved agents. Letermovir (LET) is approved …
Incidence of venous thromboembolism in coronavirus disease 2019: an experience from a single large academic center
…, G Cohen, GJ Criner, ET Choi, A Mishkin… - Journal of Vascular …, 2021 - Elsevier
Background Infection with the novel severe acute respiratory syndrome coronavirus 2 has
been associated with a hypercoagulable state. Emerging data from China and Europe have …
been associated with a hypercoagulable state. Emerging data from China and Europe have …
Vaccine effectiveness against long COVID in children
…, CR Horowitz, R Jhaveri, S Kim, A Mishkin… - …, 2024 - publications.aap.org
OBJECTIVES Vaccination reduces the risk of acute coronavirus disease 2019 (COVID-19)
in children, but it is less clear whether it protects against long COVID. We estimated vaccine …
in children, but it is less clear whether it protects against long COVID. We estimated vaccine …
Optimal sets and solution paths of ReLU networks
We develop an analytical framework to characterize the set of optimal ReLU neural networks
by reformulating the non-convex training problem as a convex program. We show that the …
by reformulating the non-convex training problem as a convex program. We show that the …
Remote patient monitoring in chronic heart failure
C Palaniswamy, A Mishkin, WS Aronow… - Cardiology in …, 2013 - journals.lww.com
Heart failure (HF) poses a significant economic burden on our health-care resources with
very high readmission rates. Remote monitoring has a substantial potential to improve the …
very high readmission rates. Remote monitoring has a substantial potential to improve the …