reproducing kernel Hilbert space
PulseAugur coverage of reproducing kernel Hilbert space — every cluster mentioning reproducing kernel Hilbert space across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
New method controls false discoveries using hypothesis structure
Researchers have developed a novel framework for controlling false discoveries in large-scale hypothesis testing by leveraging the inherent structure within hypotheses. This method reframes structured FDR control as a r…
-
New paper explores convex-geometric bounds for positive-weight kernel quadrature
Researchers have developed new theoretical bounds for positive-weight kernel quadrature, a method that can outperform Monte Carlo techniques for smooth integrands. The study shows that optimizing quadrature weights unde…
-
核仿射包络机提供计算高效的语义编码
研究人员开发了核仿射包络机（KAHMs），以提高基于Transformer的检索系统中语义编码的效率。这些机器在指定的RKHS中估计原型混合权重，并通过归一化最小均方误差来优化原型，以降低在线查询编码成本。KAHMs在奥地利法律基准测试中表现出色，实现了强大的重建指标，并将每查询延迟降低了8.5倍，相比直接Transformer编码。
-
New framework unifies kernel embedding methods for conditional distribution comparison
Researchers have introduced a unified framework called conditional maximum mean discrepancy (CMMD) to measure differences between conditional distributions. This framework encompasses various kernel-based metrics, inclu…
-
New research explores activation functions beyond ReLU in neural networks
A new paper explores the theoretical underpinnings of neural network kernels, specifically focusing on activation functions beyond the standard ReLU. Researchers characterized the Reproducing Kernel Hilbert Spaces (RKHS…
-
研究人员开发了用于学习具有算子值核的算子的 SGD 算法
研究人员开发了一种在统计逆问题中估计回归算子 的新方法。该方法利用正则化随机梯度下降 (SGD) 和算子值核，为预测和估计误差提供了与维度无关的界限。该技术提供了接近最优的收敛速度和高概率估计，适用于结构化预测和参数化偏微分方程。
-
New method tackles dynamic regret in RKHS using subspace approximation
Researchers have developed a new method for online regression in reproducing kernel Hilbert spaces (RKHS) that addresses dynamic regret. The approach adapts finite-dimensional techniques to the RKHS setting using subspa…
-
Researchers explore robust out-of-distribution optimization and stochastic function maximization
Researchers have introduced a novel framework for robust out-of-distribution stochastic optimization, designed to make effective decisions even when historical data does not perfectly match the target distribution. This…