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.
- instance of ScienceCast 95%
- instance of Gotit.pub 95%
- instance of CatalyzeX 70%
- used by CORE Recommender 70%
- instance of Influence Flower 70%
- instance of CORE Recommender 70%
- instance of CatalyzeX Code Finder for Papers 70%
- used by alphaXiv 60%
- uses CatalyzeX 60%
- used by Gotit.pub 60%
- used by ScienceCast 60%
- instance of alphaXiv 60%
6 day(s) with sentiment data
-
New method for dimension reduction with multimodal predictors introduced
This paper introduces a new method for sufficient dimension reduction in regression problems involving both a standard Euclidean predictor and a predictor object from a general metric space. The approach embeds the pred…
-
GP-UCB algorithm achieves nearly optimal regret in noise-free bandits
A new paper on arXiv introduces a theoretical analysis of the Gaussian Process Upper Confidence Bound (GP-UCB) algorithm for noise-free Gaussian Process bandits. The research demonstrates that GP-UCB achieves a nearly o…
-
New Anchored SVGD Algorithm Developed for Non-Smooth Sampling
Researchers have developed a new algorithm called Anchored Stein Variational Gradient Descent (SVGD) designed for sampling from target densities that may be non-smooth. This method introduces a smoother reference potent…
-
New PGD algorithm sharpens neural network regression rates
Researchers have developed a new Preconditioned Gradient Descent (PGD) algorithm for training over-parameterized neural networks in nonparametric regression tasks. This method, combined with early stopping, achieves a s…
-
New theory defines optimal regret for kernel-based reinforcement learning
Researchers have developed a new theoretical framework for understanding minimax regret in kernel-based reinforcement learning. The study focuses on scenarios with continuous state and action spaces and adversarial init…
-
New statistical framework uses kernel mean embeddings for distributional data analysis
Researchers have developed a new statistical framework for analyzing random probability distributions using kernel mean embeddings within reproducing kernel Hilbert spaces. This approach provides a rigorous foundation f…
-
Phase transition observed in neural network training dynamics
Researchers have identified a phase transition pattern in the approximation bounds and training errors of partially trainable neural networks. These networks combine fixed random features with adaptable representations,…
-
Quantum kernels' expressivity linked to data structure
Researchers have theoretically characterized the function class represented by Instantaneous Quantum Polynomial (IQP) feature map quantum kernels. They derived a Fourier representation of the associated Reproducing Kern…
-
New SKG reasoning engine unifies geometric laws with data induction
Researchers have introduced the Symplectic-Kernel Gradient (SKG) reasoning engine, a novel framework designed to unify geometric evolution under law constraints with data-driven induction. The SKG engine integrates conc…
-
New arXiv papers explore kernel methods for advanced time-series forecasting
Two new arXiv papers introduce advanced kernel methods for time-series forecasting. The first, "Deep Time-series Forecasting Needs Kernelized Moment Balancing," by Licheng Pan and colleagues, proposes KMB-DF to improve …
-
llama.cpp releases GPU fix; new research on random projections published
The llama.cpp project has released version b11847, which includes fixes for bf16 WMMA operand vector types on RDNA 3 and RDNA 4 GPUs. This update addresses compilation errors related to short and __bf16 types, ensuring …
-
New method uses Koopman operators for rare transition sampling
Researchers have developed a novel approach to transition path sampling (TPS) in dynamical systems, particularly for molecular dynamics, by leveraging Koopman operators and exit-time optimal control. This method address…
-
New L0MO method advances Bayesian Optimization on function spaces
Researchers have introduced a novel approach called L0 Manifold Optimization (L0MO) for Functional Bayesian Optimization (FBO). This method searches within a Reproducing Kernel Hilbert Space (RKHS) by optimizing both th…
-
New Framework for Stochastic Optimal Control and Option Pricing
This paper delves into the theoretical underpinnings of stochastic optimal control in discrete time, proposing a novel dynamic programming framework. It introduces methods for estimating the value function using nonpara…
-
New method uses prequential e-values for auditable near-optimality certificates in GP optimization
Researchers have developed a new method using prequential e-values to create auditable certificates for near-optimal solutions in sequential black-box function optimization. This approach addresses the common practice o…
-
New Functional Tucker Decomposition Enhances Tensor Analysis
Researchers have developed a novel functional Tucker decomposition (FTD) that embeds continuity constraints into tensor factorization. This method models continuous modes as functions within a reproducing kernel Hilbert…
-
New kernel method adapts to learned multivariable structure for function approximation
Researchers have introduced total sensitivity kernels (TSKs), a novel method designed to improve the approximation of complex multivariable black-box functions using limited data. TSKs leverage weighted ANOVA kernels th…
-
New RKHS method advances density ratio estimation for continuous outputs
Researchers have developed a novel spectral regularization method within a reproducing kernel Hilbert space (RKHS) to address density ratio estimation and importance-weighted regression challenges in continuous output s…
-
New research explores neural network approximation for complex functional operators · 3 sources tracked
Researchers are exploring advanced neural network architectures for approximating complex functions. One paper details how deep ReLU networks can approximate smooth functionals on infinite-dimensional Hilbert spaces, es…
-
New method improves Kernel PCA for streaming data
Researchers have developed a new method for Kernel Principal Component Analysis (KPCA) designed to handle streaming data and adapt to changes over time. This rotation-based subspace tracking approach updates the model b…