Papers › Randomized K-FACs: Speeding up K-FAC with Randomized Numerical Linear Algebra

Randomized K-FACs: Speeding up K-FAC with Randomized Numerical Linear Algebra

30 Jun 2022arXiv:2206.15397archive 2025-07-28

Constantin Octavian Puiu

K-FAC is a successful tractable implementation of Natural Gradient for Deep Learning, which nevertheless suffers from the requirement to compute the inverse of the Kronecker factors (through an eigen-decomposition). This can be very time-consuming (or even prohibitive) when these factors are large. In this paper, we theoretically show that, owing to the exponential-average construction paradigm of the Kronecker factors that is typically used, their eigen-spectrum must decay. We show numerically that in practice this decay is very rapid, leading to the idea that we could save substantial computation by only focusing on the first few eigen-modes when inverting the Kronecker-factors. Importantly, the spectrum decay happens over a constant number of modes irrespectively of the layer width. This allows us to reduce the time complexity of K-FAC from cubic to quadratic in layer width, partially closing the gap w.r.t. SENG (another practical Natural Gradient implementation for Deep learning which scales linearly in width). Randomized Numerical Linear Algebra provides us with the necessary tools to do so. Numerical results show we obtain ≈2.5× reduction in per-epoch time and ≈3.3× reduction in time to target accuracy. We compare our proposed K-FAC sped-up versions SENG, and observe that for CIFAR10 classification with VGG16_bn we perform on par with it.

PaperPDFCode

Code

constantinpuiu/randomized-kfacs officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections