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 …

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 …

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 …

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 …

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 …

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 …

We revisit the stochastic variance-reduced policy gradient (SVRPG) method proposed
by\citet {papini2018stochastic} for reinforcement learning. We provide an improved …

Stochastic AUC maximization has garnered an increasing interest due to better fit to
imbalanced data classification. However, existing works are limited to stochastic AUC …

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 …

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 …