We propose Predict then Interpolate (PI), a simple algorithm for learning
correlations that are stable across environments. The algorithm follows from
the intuition that when using a classifier trained on one environment to make
predictions on examples from another environment, its mistakes are informative
as to which correlations are unstable. In this work, we prove that by
interpolating the distributions of the correct predictions and the wrong
predictions, we can uncover an oracle distribution where the unstable
correlation vanishes. Since the oracle interpolation coefficients are not
accessible, we use group distributionally robust optimization to minimize the
worst-case risk across all such interpolations. We evaluate our method on both
text classification and image classification. Empirical results demonstrate
that our algorithm is able to learn robust classifiers (outperforms IRM by
23.85% on synthetic environments and 12.41% on natural environments). Our code
and data are available at this https URL

本文提出了一种名为 Predict then Interpolate (PI) 的算法，通过使用分类器在一个环境中训练并将其用于另一个环境中进行预测的错误来揭示不稳定的相关性，然后使用群组分布稳健优化来最小化所有插值的最坏情况风险，通过实验证明，该算法在文本分类和图像分类中均具有优越的性能。

预测再插值：一种学习稳定分类器的简单算法

Predict then Interpolate: A Simple Algorithm to Learn Stable Classifiers

This paper first presents a theory for generative adversarial methods that
does not rely on the traditional minimax formulation. It shows that with a
strong discriminator, a good generator can be learned so that the KL divergence
between the distributions of real data and generated data improves after each
functional gradient step until it converges to zero. Based on the theory, we
propose a new stable generative adversarial method. A theoretical insight into
the original GAN from this new viewpoint is also provided. The experiments on
image generation show the effectiveness of our new method.

本文提出了一种不依赖于传统极小 - 极大公式的生成式对抗方法理论，并展示了当存在强的辨别器时，通过每个功能性梯度步骤，可以学到一个好的生成器，使得真实数据和生成数据的分布的 KL 散度改善，直到收敛于零，并基于该理论，提出了一种新的稳定的生成式对抗方法，同时提供了从这个新的视角对原始 GAN 的理论洞见，最终，针对图像生成的实验展示了我们的新方法的有效性。