Multi-objective Optimization

373 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The Natural Language Decathlon: Multitask Learning as Question Answering (2018, background): “Multi-objective optimization [Deb, 2014] naturally connects to multitask learning and typically involves querying a decision-maker who weighs different objectives.”
Economic and life cycle environmental optimization of forest-based biorefinery supply chains for bioenergy and biofuel production (2016, positive): “The ε-constraint method is one of the most widely used generating approaches (Deb, 2005).”
Compressing Large-Scale Transformer-Based Models: A Case Study on BERT (2020, neutral): “For uniformity, all model sizes and speedups reported here are for the ﬁnal complete model after compression and are compared against BERT BASE , even if the method was originally applied to BERT LARGE .”
Multi-objective multi-agent decision making: a utility-based analysis and survey (2019, background): “Multi-objective optimisation (MOO) [21] approaches consider these possibly conﬂicting objectives explicitly.”
EAT-NAS: elastic architecture transfer for accelerating large-scale neural architecture search (2019, methodology): “ion. Some constraints are added to the scale of the model within an acceptable range to avoid the memory running out of control during search. On CIFAR-10, the total expansion ratio is limited within [4, 10]. For training during the search process, the batch size is set as 128. We use SGD optimizer ”