Matches in SemOpenAlex for { <https://semopenalex.org/work/W3193363485> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W3193363485 abstract "A key challenge in scaling Gaussian Process (GP) regression to massive datasets is that exact inference requires computation with a dense n x n kernel matrix, where n is the number of data points. Significant work focuses on approximating the kernel matrix via interpolation using a smaller set of m inducing points. Structured kernel interpolation (SKI) is among the most scalable methods: by placing inducing points on a dense grid and using structured matrix algebra, SKI achieves per-iteration time of O(n + m log m) for approximate inference. This linear scaling in n enables inference for very large data sets; however the cost is per-iteration, which remains a limitation for extremely large n. We show that the SKI per-iteration time can be reduced to O(m log m) after a single O(n) time precomputation step by reframing SKI as solving a natural Bayesian linear regression problem with a fixed set of m compact basis functions. With per-iteration complexity independent of the dataset size n for a fixed grid, our method scales to truly massive data sets. We demonstrate speedups in practice for a wide range of m and n and apply the method to GP inference on a three-dimensional weather radar dataset with over 100 million points." @default.
- W3193363485 created "2021-08-30" @default.
- W3193363485 creator A5000576264 @default.
- W3193363485 creator A5023229845 @default.
- W3193363485 creator A5061155671 @default.
- W3193363485 date "2021-04-01" @default.
- W3193363485 modified "2023-09-24" @default.
- W3193363485 title "Faster Kernel Interpolation for Gaussian Processes" @default.
- W3193363485 hasPublicationYear "2021" @default.
- W3193363485 type Work @default.
- W3193363485 sameAs 3193363485 @default.
- W3193363485 citedByCount "0" @default.
- W3193363485 crossrefType "journal-article" @default.
- W3193363485 hasAuthorship W3193363485A5000576264 @default.
- W3193363485 hasAuthorship W3193363485A5023229845 @default.
- W3193363485 hasAuthorship W3193363485A5061155671 @default.
- W3193363485 hasConcept C104114177 @default.
- W3193363485 hasConcept C11413529 @default.
- W3193363485 hasConcept C118615104 @default.
- W3193363485 hasConcept C121332964 @default.
- W3193363485 hasConcept C122280245 @default.
- W3193363485 hasConcept C12267149 @default.
- W3193363485 hasConcept C137800194 @default.
- W3193363485 hasConcept C154945302 @default.
- W3193363485 hasConcept C163716315 @default.
- W3193363485 hasConcept C33923547 @default.
- W3193363485 hasConcept C41008148 @default.
- W3193363485 hasConcept C61326573 @default.
- W3193363485 hasConcept C62520636 @default.
- W3193363485 hasConcept C74193536 @default.
- W3193363485 hasConceptScore W3193363485C104114177 @default.
- W3193363485 hasConceptScore W3193363485C11413529 @default.
- W3193363485 hasConceptScore W3193363485C118615104 @default.
- W3193363485 hasConceptScore W3193363485C121332964 @default.
- W3193363485 hasConceptScore W3193363485C122280245 @default.
- W3193363485 hasConceptScore W3193363485C12267149 @default.
- W3193363485 hasConceptScore W3193363485C137800194 @default.
- W3193363485 hasConceptScore W3193363485C154945302 @default.
- W3193363485 hasConceptScore W3193363485C163716315 @default.
- W3193363485 hasConceptScore W3193363485C33923547 @default.
- W3193363485 hasConceptScore W3193363485C41008148 @default.
- W3193363485 hasConceptScore W3193363485C61326573 @default.
- W3193363485 hasConceptScore W3193363485C62520636 @default.
- W3193363485 hasConceptScore W3193363485C74193536 @default.
- W3193363485 hasLocation W31933634851 @default.
- W3193363485 hasOpenAccess W3193363485 @default.
- W3193363485 hasPrimaryLocation W31933634851 @default.
- W3193363485 hasRelatedWork W1940743563 @default.
- W3193363485 hasRelatedWork W2073647817 @default.
- W3193363485 hasRelatedWork W2115964863 @default.
- W3193363485 hasRelatedWork W2166505687 @default.
- W3193363485 hasRelatedWork W2401243292 @default.
- W3193363485 hasRelatedWork W2553813446 @default.
- W3193363485 hasRelatedWork W2612312463 @default.
- W3193363485 hasRelatedWork W2809347089 @default.
- W3193363485 hasRelatedWork W2886596322 @default.
- W3193363485 hasRelatedWork W2914016960 @default.
- W3193363485 hasRelatedWork W2949493409 @default.
- W3193363485 hasRelatedWork W2951713178 @default.
- W3193363485 hasRelatedWork W2963378877 @default.
- W3193363485 hasRelatedWork W2964077839 @default.
- W3193363485 hasRelatedWork W3002385791 @default.
- W3193363485 hasRelatedWork W3005337135 @default.
- W3193363485 hasRelatedWork W3046563104 @default.
- W3193363485 hasRelatedWork W3126892819 @default.
- W3193363485 hasRelatedWork W3159158650 @default.
- W3193363485 hasRelatedWork W3195105183 @default.
- W3193363485 hasVolume "130" @default.
- W3193363485 isParatext "false" @default.
- W3193363485 isRetracted "false" @default.
- W3193363485 magId "3193363485" @default.
- W3193363485 workType "article" @default.