TensorFlowでQMC(Quasi Monte Carlo)を使っている例を探していて、別のQMC利用を見つけた。
A lot of improvement for the GPU renderer is the licensing of QMC sampling from NVIDIA. The QMC (Quasi-Monte Carlo) method uses low-discrepancy sequences instead of pseudorandom number generators. In layman terms this means the distribution seems more random - while not being - but avoids the clumping that is natural in random or pseduorandom sequences. The more evenly random the samples, the less samples for the same perceived anti-alising or noise for example. Chaos licensed this from NVIDIA (which uses it in Mental Ray/iRay). This is important for Chaos as the GPU renderer uses random sampling much more than the CPU production renderer, and thus uses the QMC to produce - in some cases - a better noise floor than the main production renderer.
サンプリングにQMCを使っている。
Mersenne Twisterを含めた従来のrandom numberと比べてavoids the clumping
とある。
積分の収束が早くなったり、MNISTの学習が早まるなどはこのavoids the clumping
というのが効いているのだろう。
なお、Neural Networkで検索していて別のQMC(Quantum Monte Calro)も見つかった。こちらは原理は未消化。
https://arxiv.org/abs/cond-mat/9807008