• Corpus ID: 235422445

SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes

  title={SKIing on Simplices: Kernel Interpolation on the Permutohedral Lattice for Scalable Gaussian Processes},
  author={Sanyam Kapoor and Marc Finzi and Ke Alexander Wang and Andrew Gordon Wilson},
State-of-the-art methods for scalable Gaussian processes use iterative algorithms, requiring fast matrix vector multiplies (MVMs) with the covariance kernel. The Structured Kernel Interpolation (SKI) framework accelerates these MVMs by performing efficient MVMs on a grid and interpolating back to the original space. In this work, we develop a connection between SKI and the permutohedral lattice used for highdimensional fast bilateral filtering. Using a sparse simplicial grid instead of a dense… 

When are Iterative Gaussian Processes Reliably Accurate?

This work investigates CG tolerance, preconditioner rank, and Lanczos decompositions, and shows that L-BFGS-B is a compelling optimizer for Iterative GPs, achieving convergence with fewer gradient updates.

Bézier Gaussian Processes for Tall and Wide Data

This work introduces a kernel that allows the number of summarising variables to grow exponentially with theNumber of input features, but requires only linear cost in both number of observations and input features.

Log-Linear-Time Gaussian Processes Using Binary Tree Kernels

The binary tree GP assigns the highest likelihood to the test data on a plurality of datasets, usually achieves lower mean squared error than the sparse methods, and often ties or beats the Matérn GP.



Fast High‐Dimensional Filtering Using the Permutohedral Lattice

This algorithm is the first implementation of a high‐dimensional Gaussian filter that is both linear in input size and polynomial in dimensionality, and achieves a consistently high accuracy relative to ground truth (> 45 dB).

Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)

A new structured kernel interpolation (SKI) framework is introduced, which generalises and unifies inducing point methods for scalable Gaussian processes (GPs) and naturally enables Kronecker and Toeplitz algebra for substantial additional gains in scalability.

Product Kernel Interpolation for Scalable Gaussian Processes

A new technique for MVM based learning that exploits product kernel structure is developed, resulting in linear rather than exponential runtime with dimension for SKI, as well as state-of-the-art asymptotic complexity for multi-task GPs.

Exact Gaussian Processes on a Million Data Points

A scalable approach for exact GPs is developed that leverages multi-GPU parallelization and methods like linear conjugate gradients, accessing the kernel matrix only through matrix multiplication, and is generally applicable, without constraints to grid data or specific kernel classes.

GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration

This work presents an efficient and general approach to GP inference based on Blackbox Matrix-Matrix multiplication (BBMM), a modified batched version of the conjugate gradients algorithm to derive all terms for training and inference in a single call.

Lattice-Based High-Dimensional Gaussian Filtering and the Permutohedral Lattice

This paper analyzes lattice-based high-dimensional Gaussian filtering algorithms, and gives a rigorous exposition of the properties of the permutohedral lattice and argues that it is the optimal lattice forGaussian filtering.

Kernel Operations on the GPU, with Autodiff, without Memory Overflows

The KeOps library provides a fast and memory-efficient GPU support for tensors whose entries are given by a mathematical formula, such as kernel and distance matrices, including PyTorch CUDA tensors or the Halide and TVM libraries.

Thoughts on Massively Scalable Gaussian Processes

The MSGP framework enables the use of Gaussian processes on billions of datapoints, without requiring distributed inference, or severe assumptions, and reduces the standard GP learning and inference complexity to O(n), and the standard test point prediction complexity to $O(1).

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

  • Hang SuV. Jampani J. Kautz
  • Computer Science
    2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2018
A network architecture for processing point clouds that directly operates on a collection of points represented as a sparse set of samples in a high-dimensional lattice that outperforms existing state-of-the-art techniques on 3D segmentation tasks.

Gaussian KD-trees for fast high-dimensional filtering

A Monte-Carlo kd-tree sampling algorithm that efficiently computes any filter that can be expressed in this way, along with a GPU implementation of this technique and a fast adaptation of non-local means to geometry.