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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Hyper-parameters optimization (HPO) is vital for machine learning models.Besides model accuracy, other tuning intentions such as model training time andenergy consumption are also worthy of attention from data analytic serviceproviders. Hence, it is essential to take both model hyperparameters and systemparameters into consideration to execute cross-layer multi-objectivehyperparameter auto-tuning. Towards this challenging target, we proposeHyperTuner in this paper. To address the formulated high-dimensional black-boxmulti-objective optimization problem, HyperTuner first conducts multi-objectiveparameter importance ranking with its MOPIR algorithm and then leverages theproposed ADUMBO algorithm to find the Pareto-optimal configuration set. Duringeach iteration, ADUMBO selects the most promising configuration from thegenerated Pareto candidate set via maximizing a new well-designed metric, whichcan adaptively leverage the uncertainty as well as the predicted mean acrossall the surrogate models along with the iteration times. We evaluate HyperTuneron our local distributed TensorFlow cluster and experimental results show thatit is always able to find a better Pareto configuration front superior in bothconvergence and diversity compared with the other four baseline algorithms.Besides, experiments with different training datasets, different optimizationobjectives and different machine learning platforms verify that HyperTuner canwell adapt to various data analytic service scenarios.

HyperTuner: A Cross-Layer Multi-Objective Hyperparameter Auto-Tuning Framework for Data Analytic Services