Recent advances in stochastic gradient descent in deep learning
In the age of artificial intelligence, the best approach to handling huge amounts of data is a
tremendously motivating and hard problem. Among machine learning models, stochastic …
tremendously motivating and hard problem. Among machine learning models, stochastic …
随机梯度下降算法研究进展
史加荣, 王丹, 尚凡华, 张鹤于 - 自动化学报, 2021 - aas.net.cn
在机器学习领域中, 梯度下降算法是求解最优化问题最重要, 最基础的方法. 随着数据规模的不断
扩大, 传统的梯度下降算法已不能有效地解决大规模机器学习问题. 随机梯度下降算法在迭代 …
扩大, 传统的梯度下降算法已不能有效地解决大规模机器学习问题. 随机梯度下降算法在迭代 …
Dash: Semi-supervised learning with dynamic thresholding
While semi-supervised learning (SSL) has received tremendous attentions in many machine
learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either …
learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either …
PAGE: A simple and optimal probabilistic gradient estimator for nonconvex optimization
In this paper, we propose a novel stochastic gradient estimator—ProbAbilistic Gradient
Estimator (PAGE)—for nonconvex optimization. PAGE is easy to implement as it is designed …
Estimator (PAGE)—for nonconvex optimization. PAGE is easy to implement as it is designed …
Stochastic recursive gradient descent ascent for stochastic nonconvex-strongly-concave minimax problems
We consider nonconvex-concave minimax optimization problems of the form $\min_ {\bf
x}\max_ {\bf y\in {\mathcal Y}} f ({\bf x},{\bf y}) $, where $ f $ is strongly-concave in $\bf y $ but …
x}\max_ {\bf y\in {\mathcal Y}} f ({\bf x},{\bf y}) $, where $ f $ is strongly-concave in $\bf y $ but …
Sample efficient policy gradient methods with recursive variance reduction
Improving the sample efficiency in reinforcement learning has been a long-standing
research problem. In this work, we aim to reduce the sample complexity of existing policy …
research problem. In this work, we aim to reduce the sample complexity of existing policy …
An improved convergence analysis of stochastic variance-reduced policy gradient
We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed
by\citet {papini2018stochastic} for reinforcement learning. We provide an improved …
by\citet {papini2018stochastic} for reinforcement learning. We provide an improved …
Stochastic auc maximization with deep neural networks
Stochastic AUC maximization has garnered an increasing interest due to better fit to
imbalanced data classification. However, existing works are limited to stochastic AUC …
imbalanced data classification. However, existing works are limited to stochastic AUC …
EF21 with bells & whistles: Practical algorithmic extensions of modern error feedback
First proposed by Seide (2014) as a heuristic, error feedback (EF) is a very popular
mechanism for enforcing convergence of distributed gradient-based optimization methods …
mechanism for enforcing convergence of distributed gradient-based optimization methods …
Improved fine-tuning by better leveraging pre-training data
As a dominant paradigm, fine-tuning a pre-trained model on the target data is widely used in
many deep learning applications, especially for small data sets. However, recent studies …
many deep learning applications, especially for small data sets. However, recent studies …