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.
6 day(s) with sentiment data
-
New theorem details fluctuations in kernel gradient flow and boosting
Researchers have established a functional central limit theorem for kernel gradient flow and infinitesimal gradient boosting. This theorem details the fluctuations of the process around its deterministic limit, showing …
-
Withdrawn arXiv paper links metric entropy to RKBS embeddability
A research paper, recently withdrawn by its author Yiping Lu, explored the relationship between metric entropy and the embeddability of function spaces into reproducing kernel Banach spaces (RKBS). The study established…
-
New research analyzes Nyström subsampling for domain adaptation
This paper delves into the convergence properties of Nyström subsampling when applied to unsupervised domain adaptation under covariate shift, specifically examining the misspecified case where the target function is ou…
-
New Kernel Test Boosts Statistical Power by Focusing on Key Directions
Researchers have developed a new kernel-based statistical test that improves upon existing methods like Maximum Mean Discrepancy (MMD). This novel approach truncates the spectral decomposition of MMD, focusing on robust…
-
New Causal Inference Method Uses Kernel Balancing for Complex Treatments
Researchers have developed a new kernel-based functional balancing method for causal inference, specifically designed for compositional treatments. This approach constructs weights by minimizing a worst-case balancing e…
-
New AI Methods Enhance Point Cloud Registration for Robotics and Surgery
Two new research papers explore advanced techniques for point cloud registration. The first, Generalized-CVO, uses Riemannian optimization to achieve up to a 10x speedup over previous methods for LiDAR and RGB-D data, s…
-
New methods enhance uncertainty quantification in large AI models
Researchers are developing new methods to improve uncertainty quantification in large models. One approach, Semantic Gaussian Process Uncertainty (SGPU), analyzes the geometric structure of answer embeddings to estimate…
-
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…
-
Kernel Affine Hull Machines offer compute-efficient semantic encoding
Researchers have developed Kernel Affine Hull Machines (KAHMs) to improve the efficiency of semantic encoding in transformer-based retrieval systems. These machines estimate prototype-mixture weights in a specified RKHS…
-
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…
-
Researchers develop SGD algorithms for learning operators with operator-valued kernels
Researchers have developed a new method for estimating regression operators in statistical inverse problems. The approach utilizes regularized stochastic gradient descent (SGD) with operator-valued kernels, offering dim…
-
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…