arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2308.04412cs.LGcs.AI
收藏

使用随机线性分类器的概率不变学习

Probabilistic Invariant Learning with Randomized Linear Classifiers

Vector Institute(向量研究所);Technion(以色列理工学院);University of Toronto(多伦多大学)

Leonardo Cotta, Gal Yehuda, Assaf Schuster, Chris J. Maddison

AI总结:

本文提出 Randomized Linear Classifiers(RLCs),以概率形式的通用逼近与不变性降低资源需求,并为集合、图和球面数据构造可证明的概率不变分类器。

摘要:

设计既具有表达能力又能保持任务已知不变性的模型正变得越来越困难。现有解决方案会在不变性与计算或内存资源之间进行权衡。在这项工作中,我们展示了如何利用随机性,设计兼具表达能力和不变性、同时使用更少资源的模型。受随机化算法启发,我们的关键洞见是:接受通用逼近和不变性的概率概念可以降低资源需求。更具体地说,我们提出了一类称为 Randomized Linear Classifiers(RLCs,随机线性分类器)的二分类模型。我们给出了参数和样本量条件,在这些条件下,RLCs 能够以高概率逼近任意(光滑)函数,同时保持对紧群变换的不变性。利用这一结果,我们设计了三种 RLCs,它们在集合、图和球面数据的分类任务上被证明具有概率不变性。我们展示了这些模型如何以比(确定性)神经网络及其不变对应模型更少的资源实现概率不变性和通用性。最后,我们在已知确定性不变神经网络会遇到困难的不变任务上,通过实验证明了这类新模型的优势。

英文摘要:

Designing models that are both expressive and preserve known invariances of tasks is an increasingly hard problem. Existing solutions tradeoff invariance for computational or memory resources. In this work, we show how to leverage randomness and design models that are both expressive and invariant but use less resources. Inspired by randomized algorithms, our key insight is that accepting probabilistic notions of universal approximation and invariance can reduce our resource requirements. More specifically, we propose a class of binary classification models called Randomized Linear Classifiers (RLCs). We give parameter and sample size conditions in which RLCs can, with high probability, approximate any (smooth) function while preserving invariance to compact group transformations. Leveraging this result, we design three RLCs that are provably probabilistic invariant for classification tasks over sets, graphs, and spherical data. We show how these models can achieve probabilistic invariance and universality using less resources than (deterministic) neural networks and their invariant counterparts. Finally, we empirically demonstrate the benefits of this new class of models on invariant tasks where deterministic invariant neural networks are known to struggle.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑