LAPLEX enables trainable Laplace kernels for high-dimensional deep learning

Researchers have introduced LAPLEX, a novel class of learnable Laplace-kernel operators designed to enable efficient, high-dimensional linear algebra in deep learning. LAPLEX layers act like full-rank dense matrices but are implicitly defined by a small set of learnable parameters, allowing for matrix-vector operations at scales up to $10^9$ dimensions on GPUs. This approach separates the expressivity of dense matrices from their storage cost, facilitating data-adaptive global interactions and enabling compact projections and interpretable soft routing models. AI

IMPACT Introduces a method to handle high-dimensional data and complex interactions efficiently in deep learning models.

RANK_REASON This is a research paper detailing a new method for linear algebra in deep learning. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Deep Learning
• Laplace Kernels
• LAPLEX

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →