论文标题
regflow：概率基于流的回归以进行未来预测
RegFlow: Probabilistic Flow-based Regression for Future Prediction
论文作者
论文摘要
预测给定系统的未来状态或行动仍然是智力的基本，尚未解决的挑战，尤其是在复杂和非确定性的场景的范围内，例如人类的建模行为。现有的方法在关于未来州的非偶体性的强烈假设下提供了结果，或者充其量是假设通常适合现实生活条件的特定概率分布。在这项工作中，我们引入了一个健壮且灵活的概率框架，该框架允许对未来的预测进行建模，几乎没有任何限制的方式或潜在的概率分布。为了实现这一目标，我们利用超网络架构并训练连续的归一化流模型。该方法称为Regflow的方法在几个基准数据集上实现了最先进的结果，从而超过了竞争的方法。
Predicting future states or actions of a given system remains a fundamental, yet unsolved challenge of intelligence, especially in the scope of complex and non-deterministic scenarios, such as modeling behavior of humans. Existing approaches provide results under strong assumptions concerning unimodality of future states, or, at best, assuming specific probability distributions that often poorly fit to real-life conditions. In this work we introduce a robust and flexible probabilistic framework that allows to model future predictions with virtually no constrains regarding the modality or underlying probability distribution. To achieve this goal, we leverage a hypernetwork architecture and train a continuous normalizing flow model. The resulting method dubbed RegFlow achieves state-of-the-art results on several benchmark datasets, outperforming competing approaches by a significant margin.
