On learning rates and schr\" odinger operators

B Shi, WJ Su, MI Jordan - arxiv preprint arxiv:2004.06977, 2020 - arxiv.org
The learning rate is perhaps the single most important parameter in the training of neural
networks and, more broadly, in stochastic (nonconvex) optimization. Accordingly, there are …

On convergence-diagnostic based step sizes for stochastic gradient descent

S Pesme, A Dieuleveut… - … Conference on Machine …, 2020 - proceedings.mlr.press
Abstract Constant step-size Stochastic Gradient Descent exhibits two phases: a transient
phase during which iterates make fast progress towards the optimum, followed by a …

Stochastic adaptive line search for differentially private optimization

C Chen, J Lee - 2020 IEEE International Conference on Big …, 2020 - ieeexplore.ieee.org
The performance of private gradient-based optimization algorithms is highly dependent on
the choice of step size (or learning rate) which often requires non-trivial amount of tuning. In …

Fair Wasserstein Coresets

Z **ong, N Dalmasso, S Sharma, F Lecue… - arxiv preprint arxiv …, 2023 - arxiv.org
Data distillation and coresets have emerged as popular approaches to generate a smaller
representative set of samples for downstream learning tasks to handle large-scale datasets …

On learning rates and Schrödinger operators

B Shi, W Su, MI Jordan - Journal of Machine Learning Research, 2023 - jmlr.org
Understanding the iterative behavior of stochastic optimization algorithms for minimizing
nonconvex functions remains a crucial challenge in demystifying deep learning. In …

Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent

X Li, Q **e - arxiv preprint arxiv:2412.11341, 2024 - arxiv.org
The convergence behavior of Stochastic Gradient Descent (SGD) crucially depends on the
stepsize configuration. When using a constant stepsize, the SGD iterates form a Markov …

X-COVNet: Externally Validated Model for Computer-Aided Diagnosis of Pneumonia-Like Lung Diseases in Chest X-Rays Based on Deep Transfer Learning

JF Martinez Pazos Jr, J Gulin Gonzales Sr… - medRxiv, 2024 - medrxiv.org
Since the appearance of COVID-19, the accurate diagnosis of pneumonia-type lung
diseases by chest radiographs has been a challenging task for experts, mainly due to the …

Higrad: Uncertainty quantification for online learning and stochastic approximation

WJ Su, Y Zhu - Journal of Machine Learning Research, 2023 - jmlr.org
Stochastic gradient descent (SGD) is an immensely popular approach for online learning in
settings where data arrives in a stream or data sizes are very large. However, despite an …

[PDF][PDF] X-COVNet: Externally Validated Model for Computer-Aided Diagnosis of Pneumonia-Like Lung Diseases in Chest X-Rays Based on Deep Transfer Learning

JFM Pazos, AO García, JG Gonzales, DB Lorenzo - Transfer, 2024 - researchgate.net
Since the appearance of COVID-19, the accurate diagnosis of pneumonia-type lung
diseases by 19 chest radiographs has been a challenging task for experts, mainly due to the …

FRESHNets: Highly Accurate and Efficient Food Freshness Assessment Based on Deep Convolutional Neural Networks

JFM Pazos, JG González, DB Lorenzo… - Inteligencia …, 2024 - journal.iberamia.org
Food freshness classification is a growing concern in the food industry, mainly to protect
consumer health and prevent illness and poisoning from consuming spoiled food. Intending …