1.2k citations · 1.3k across the 27 of their papers we have counts for
3 papers · 1 filter
Approximately Exact Line Search
Sara Fridovich-Keil, Benjamin Recht
We propose approximately exact line search (AELS), which uses only function evaluations to select a step size within a constant fraction of the exact line search minimizer of a uni…
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
Matthew Tancik, Pratul P. Srinivasan, Ben Mildenhall +6
We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in low-dimensional problem domain…
Neural Kernels Without Tangents
Vaishaal Shankar, Alex Fang, Wenshuo Guo +4
We investigate the connections between neural networks and simple building blocks in kernel space. In particular, using well established feature space tools such as direct sum, ave…