English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep neural networks (DNNs) are ubiquitous in computer vision and naturallanguage processing, but suffer from high inference cost. This problem can beaddressed by quantization, which consists in converting floating pointperations into a lower bit-width format. With the growing concerns on privacyrights, we focus our efforts on data-free methods. However, such techniquessuffer from their lack of adaptability to the target devices, as a hardwaretypically only support specific bit widths. Thus, to adapt to a variety ofdevices, a quantization method shall be flexible enough to find good accuracyv.s. speed trade-offs for every bit width and target device. To achieve this,we propose PIPE, a quantization method that leverages residual error expansion,along with group sparsity and an ensemble approximation for betterparallelization. PIPE is backed off by strong theoretical guarantees andachieves superior performance on every benchmarked application (from vision toNLP tasks), architecture (ConvNets, transformers) and bit-width (from int8 toternary quantization).

PIPE : Parallelized Inference Through Post-Training Quantization Ensembling of Residual Expansions