J
Jacob R. Gardner
Researcher at Cornell University
Publications - 54
Citations - 2881
Jacob R. Gardner is an academic researcher from Cornell University. The author has contributed to research in topics: Gaussian process & Computer science. The author has an hindex of 21, co-authored 43 publications receiving 2008 citations. Previous affiliations of Jacob R. Gardner include Uber & University of Pennsylvania.
Papers
More filters
Posted Content
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration.
TL;DR: 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.
Proceedings Article
Bayesian Optimization with Inequality Constraints
TL;DR: This work presents constrained Bayesian optimization, which places a prior distribution on both the objective and the constraint functions, and evaluates this method on simulated and real data, demonstrating that constrainedBayesian optimization can quickly find optimal and feasible points, even when small feasible regions cause standard methods to fail.
Proceedings Article
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration
TL;DR: In this article, the authors present an efficient and general approach to GP inference based on Blackbox Matrix-Matrix multiplication (BBMM), which uses a modified batched version of the conjugate gradient algorithm to derive all terms for training and inference in a single call.
Proceedings ArticleDOI
Deep Feature Interpolation for Image Content Changes
Paul Upchurch,Jacob R. Gardner,Geoff Pleiss,Robert Pless,Noah Snavely,Kavita Bala,Kilian Q. Weinberger +6 more
TL;DR: Deep Feature Interpolation (DFI) as mentioned in this paper is a data-driven baseline for automatic high-resolution image transformation, which relies only on simple linear interpolation of deep convolutional features from pre-trained convnets.
Proceedings Article
Simple Black-box Adversarial Attacks
TL;DR: In contrast to the white-box scenario, constructing black-box adversarial images has the additional constraint on query budget, and efficient attacks remain an open problem to date as discussed by the authors.