# Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian Processes Source: [Finding Non-Uniform Quantization Schemes using Multi-Task Gaussian Processes]() Collection index: [llms.txt]() Data updated: 2025-10-25T22:25:59.816Z Authors: Marcelo Gennari do Nascimento, Theo W. Costain, Victor Adrian Prisacariu Published: 2020-07-15T15:16:18.000Z ## Abstract We propose a novel method for neural network quantization that casts the neural architecture search problem as one of hyperparameter search to find non-uniform bit distributions throughout the layers of a CNN. We perform the search assuming a Multi-Task Gaussian Processes prior, which splits the problem to multiple tasks, each corresponding to different number of training epochs, and explore the space by sampling those configurations that yield maximum information. We then show that with significantly lower precision in the last layers we achieve a minimal loss of accuracy with appreciable memory savings. We test our findings on the CIFAR10 and ImageNet datasets using the VGG, ResNet and GoogLeNet architectures. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()