no code implementations • 7 Oct 2023 • Isaac Reid, Krzysztof Choromanski, Eli Berger, Adrian Weller
This includes many of the most popular examples of kernels defined on the nodes of a graph.
no code implementations • 7 Oct 2023 • Isaac Reid, Eli Berger, Krzysztof Choromanski, Adrian Weller
We present a novel quasi-Monte Carlo mechanism to improve graph-based sampling, coined repelling random walks.
1 code implementation • 31 Jan 2023 • Isaac Reid, Krzysztof Choromanski, Valerii Likhosherstov, Adrian Weller
We present Simplex Random Features (SimRFs), a new random feature (RF) mechanism for unbiased approximation of the softmax and Gaussian kernels by geometrical correlation of random projection vectors.
no code implementations • 10 Mar 2021 • Shuofeng Zhang, Isaac Reid, Guillermo Valle Pérez, Ard Louis
As an alternative to flatness measures, we use a function based picture and propose using the log of Bayesian prior upon initialization, $\log P(f)$, as a predictor of the generalization when a DNN converges on function $f$ after training to zero error.