Unsupervised domain adaptation is used in many machine learning applications
where, during training, a model has access to unlabeled data in the target
domain, and a related labeled dataset. In this paper, we introduce a novel and
general domain-adversarial framework. Specifically, we derive a novel
generalization bound for domain adaptation that exploits a new measure of
discrepancy between distributions based on a variational characterization of
f-divergences. It recovers the theoretical results from Ben-David et al.
(2010a) as a special case and supports divergences used in practice. Based on
this bound, we derive a new algorithmic framework that introduces a key
correction in the original adversarial training method of Ganin et al. (2016).
We show that many regularizers and ad-hoc objectives introduced over the last
years in this framework are then not required to achieve performance comparable
to (if not better than) state-of-the-art domain-adversarial methods.
Experimental analysis conducted on real-world natural language and computer
vision datasets show that our framework outperforms existing baselines, and
obtains the best results for f-divergences that were not considered previously
in domain-adversarial learning.

本文提出了一种新的通用领域敌对框架，利用变分 f - 分歧的特征进行领域自适应。基于此框架，推导出了具有重要修正的新算法框架，并证明了其在自然语言和计算机视觉数据集上优于现有的基线结果。

f 域对抗学习：理论与算法

f-Domain-Adversarial Learning: Theory and Algorithms

In this work, we improve upon the stepwise analysis of noisy iterative
learning algorithms initiated by Pensia, Jog, and Loh (2018) and recently
extended by Bu, Zou, and Veeravalli (2019). Our main contributions are
significantly improved mutual information bounds for Stochastic Gradient
Langevin Dynamics via data-dependent estimates. Our approach is based on the
variational characterization of mutual information and the use of
data-dependent priors that forecast the mini-batch gradient based on a subset
of the training samples. Our approach is broadly applicable within the
information-theoretic framework of Russo and Zou (2015) and Xu and Raginsky
(2017). Our bound can be tied to a measure of flatness of the empirical risk
surface. As compared with other bounds that depend on the squared norms of
gradients, empirical investigations show that the terms in our bounds are
orders of magnitude smaller.

本文改进了 Pensia，Jog 和 Loh (2018) 开始的有噪声迭代学习算法的逐步分析，并在 Bu，Zou 和 Veeravalli (2019) 的基础上最近扩展。我们主要的贡献是通过数据相关估计显著提高了随机梯度 Langevin 动力学的互信息界限。我们的方法基于互信息的变分特性和使用基于训练样本子集的数据相关先验来预测小批量梯度。我们的方法在 Russo 和 Zou (2015)、Xu 和 Raginsky (2017) 的信息论框架内广泛适用。与其他依赖于梯度平方范数的边界相比，我们的边界项的数量级要小得多，同时可以与经验风险面的平坦度指标相关联。

通过数据依赖估计的信息理论广义绑定对 SGLD 的应用

Information-Theoretic Generalization Bounds for SGLD via Data-Dependent  Estimates

Here, we consider numerical methods for stationary mean-field games (MFG) and
investigate two classes of algorithms. The first one is a gradient-flow method
based on the variational characterization of certain MFG. The second one uses
monotonicity properties of MFG. We illustrate our methods with various
examples, including one-dimensional periodic MFG, congestion problems, and
higher-dimensional models.

本文研究了两种解决平稳均场博弈的数值方法：基于变分特征的梯度流方法和利用单调性质的方法，并通过各种实例，包括一维周期性 MFG、拥堵问题和高维模型进行展示。