当前位置:
X-MOL 学术
›
arXiv.cs.LG
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
RegFlow: Probabilistic Flow-based Regression for Future Prediction
arXiv - CS - Machine Learning Pub Date : 2020-11-30 , DOI: arxiv-2011.14620 Maciej Zięba, Marcin Przewięźlikowski, Marek Śmieja, Jacek Tabor, Tomasz Trzcinski, Przemysław Spurek
arXiv - CS - Machine Learning Pub Date : 2020-11-30 , DOI: arxiv-2011.14620 Maciej Zięba, Marcin Przewięźlikowski, Marek Śmieja, Jacek Tabor, Tomasz Trzcinski, Przemysław Spurek
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.
中文翻译:
RegFlow:基于概率流的回归以进行未来预测
预测给定系统的未来状态或动作仍然是智能的一项基本但尚未解决的挑战,特别是在复杂且不确定的情况下,例如对人类行为建模。现有方法在有关未来状态的单峰性的强大假设下提供了结果,或者最多只能假设通常不太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而灵活的概率框架,该框架可以对未来的预测进行建模,而对模式或潜在的概率分布几乎没有任何限制。为了实现此目标,我们利用超网络体系结构并训练连续的标准化流模型。所得的称为RegFlow的方法可在多个基准数据集上获得最新的结果,
更新日期:2020-12-01
中文翻译:
RegFlow:基于概率流的回归以进行未来预测
预测给定系统的未来状态或动作仍然是智能的一项基本但尚未解决的挑战,特别是在复杂且不确定的情况下,例如对人类行为建模。现有方法在有关未来状态的单峰性的强大假设下提供了结果,或者最多只能假设通常不太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而灵活的概率框架,该框架可以对未来的预测进行建模,而对模式或潜在的概率分布几乎没有任何限制。为了实现此目标,我们利用超网络体系结构并训练连续的标准化流模型。所得的称为RegFlow的方法可在多个基准数据集上获得最新的结果,