On learning rates and schr\" odinger operators
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 …
networks and, more broadly, in stochastic (nonconvex) optimization. Accordingly, there are …
On convergence-diagnostic based step sizes for stochastic gradient descent
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 …
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 …
the choice of step size (or learning rate) which often requires non-trivial amount of tuning. In …
Fair Wasserstein Coresets
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 …
representative set of samples for downstream learning tasks to handle large-scale datasets …
On learning rates and Schrödinger operators
Understanding the iterative behavior of stochastic optimization algorithms for minimizing
nonconvex functions remains a crucial challenge in demystifying deep learning. In …
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 …
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 …
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 …
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 …
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
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 …
consumer health and prevent illness and poisoning from consuming spoiled food. Intending …