AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Differentiable Compositional Kernel Learning for Gaussian Processes

Shengyang Sun, Guodong Zhang, Chaoqi Wang, Wenyuan Zeng, Jiaman Li, Roger Grosse

ICML 2018 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Infinite-width networks as Gaussian processes · 43 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use NKN instead of GP-RBFGaussian-process regression · UCI random-split benchmarks: Boston, Energy, Pow. Plant, Wine, YachtTest RMSE: Boston: 2.753±0.137 -> 2.506±0.150; Energy: 0.471±0.013 -> 0.254±0.020; Pow. Plant: 3.014±0.068 -> 2.675±0.074; Wine: 0.Improved
Use NKN instead of GP-RBFGaussian-process regression · UCI random-split benchmarks: Boston, Concrete, Energy, Kin8nm, Naval, Pow. Plant, Wine, YachtTest log-likelihood: Boston: -2.434±0.069 -> -2.394±0.080; Concrete: -2.948±0.025 -> -2.842±0.263; Energy: -0.673±0.035 -> -0.213±0.162; Kin8Mixed
Use NKN instead of GP-SM4Gaussian-process regression · UCI random-split benchmarks: Boston, Energy, Pow. Plant, Wine, YachtTest RMSE: Boston: 2.979±0.162 -> 2.506±0.150; Energy: 0.316±0.018 -> 0.254±0.020; Pow. Plant: 2.781±0.071 -> 2.675±0.074; Wine: 0.Improved
Use NKN instead of GP-SM4Gaussian-process regression · UCI random-split benchmarks: Concrete, Energy, Kin8nm, Naval, Pow. Plant, Wine, YachtTest log-likelihood: Concrete: -2.662±0.053 -> -2.842±0.263; Energy: -0.320±0.089 -> -0.213±0.162; Kin8nm: 1.387±0.006 -> 1.291±0.006; Naval:Mixed
Use NKN instead of GP-SMGaussian-process regression · PCA-split regression benchmarksTest RMSE: Boston: 8.600 -> 4.658; Concrete: 7.591 -> 6.242; Energy: 0.447 -> 0.459; Kin8nm: 0.065 -> 0.086; Naval: 0.000 -> 0.000;Mixed
Use NKN instead of GP-SMGaussian-process regression · PCA-split regression benchmarksTest log-likelihood: Boston: -4.404 -> -3.557; Concrete: -3.285 -> -3.112; Energy: -0.564 -> -0.649; Kin8nm: 1.322 -> 1.057; Naval: 9.037 -> Mixed
Replace heuristic sum kernel with compositional NKNAirline time-series GP · Airline extrapolationextrapolation qualityImproved
Replace Automatic Statistician with NKNAirline time-series kernel learning · Airline training timetraining time (seconds): 6147 seconds -> 201 secondsImproved
Use NKN instead of SM kernelTexture extrapolation · Metal thread plate and paved patternvisual reconstruction qualityImproved
Use NKN instead of generic RBF kernelBayesian optimization with Expected Improvement · Three additive toy-function benchmarksbest function valueImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy