SIKA-GP：利用稀疏诱导核近似加速贝叶斯深度学习中的高斯过程推断
SIKA-GP: Accelerating Gaussian Process Inference with Sparse Inducing Kernel Approximations for Bayesian Deep Learning
AI总结：
提出SIKA-GP方法，通过基于二元有序模板基的稀疏诱导核近似，将高斯过程推断的计算复杂度降低至O(log M)，并实现高效张量化GPU计算，可自然嵌入贝叶斯神经网络，在视觉和Transformer语言基准上显著加速训练和推断而不牺牲预测性能。
摘要：
高斯过程（GPs）为不确定性估计提供了原则性的贝叶斯框架，但其计算复杂度严重限制了在大规模数据集上的可扩展性。我们提出SIKA-GP，该方法使用基于二元有序模板基的稀疏诱导核近似来加速GP推断，对诱导点数量的复杂度依赖仅为${O}(\log M)$。我们的方法从稀疏激活基构建紧凑且表达力强的核表示，从而实现高效的张量化GPU计算，并与现代大规模模型无缝集成。SIKA-GP可以自然地嵌入具有稀疏激活的贝叶斯神经网络（BNNs）中，在训练和推断中均实现显著加速，且不牺牲预测性能。该方法自然地扩展到深度特征学习，解决了深度架构和高维特征表示带来的可扩展性挑战。在视觉和基于Transformer的语言基准上的实验结果表明，我们的方法始终提供快速且准确的GP模型，为可扩展核学习提供了一条原则性路径。
英文摘要：
Gaussian processes (GPs) provide a principled Bayesian framework for uncertainty estimation, but their computational complexity severely limits scalability to large datasets. We propose SIKA-GP, which accelerates GP inference using sparse inducing kernel approximations based on a dyadic ordered template basis, incurring only ${O}(\log M)$ complexity dependence on the number of inducing points. Our approach constructs compact and expressive kernel representations from sparsely activated bases, enabling efficient tensorized GPU computation and seamless integration with modern large-scale models. SIKA-GP can be naturally embedded into Bayesian neural networks (BNNs) with sparse activations, yielding significant speedups in both training and inference without sacrificing predictive performance. The method naturally extends to deep feature learning, addressing the scalability challenges introduced by deep architectures and high-dimensional feature representations. Empirical results on vision and transformer-based language benchmarks demonstrate that our approach consistently delivers fast and accurate GP models, providing a principled path toward scalable kernel learning.
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。
