Multi-objective Architecture Search for CNNs

By Thomas Elsken, Jan Hendrik Metzen, Frank Hutter. 2018

59 citations recorded by the source corpus.

Subfields: Neural Architecture Search & AutoML

How researchers see this paper

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

In Neural Architecture Search & AutoML

Citations in the corpus

NAS-Bench-101: Towards Reproducible Neural Architecture Search (2019, background): “, 2018b) or network morphisms (Cai et al., 2018; Elsken et al., 2018) cannot be directly evaluated on the dataset, so we did not include them.”
Random Search and Reproducibility for Neural Architecture Search (2019, background): “fferent directions. New approaches introduce a significant amount of algorithmic complexity in the search process, including complicated training routines [1, 7, 41, 47], architecture transformations [6, 11, 32, 43, 46], and modeling assumptions [5, 23, 26, 31, 50] (see Figure 1 and Section 1.1 for ”
ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware (2018, background): “Therefore, it is a multi-objective NAS task (Hsu et al., 2018; Dong et al., 2018; Elsken et al., 2018a; He et al., 2018; Wang et al., 2018; Tan et al., 2018), where one of the objectives is non-differentiable (i.e. latency).”
Graph HyperNetworks for Neural Architecture Search (2018, methodology): “While earlier NAS methods focused on standard image classiﬁcation and language modeling, recent literature has extended NAS to search for architectures that are computationally efﬁcient (Tan et al., 2018; Dong et al., 2018; Hsu et al., 2018; Elsken et al., 2018; Zhou et al., 2018).”
Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search (2018, background): “Recent work on neural architecture search (NAS) (Baker et al., 2017; Pham et al., 2018; Zoph and Le, 2017; Real et al., 2017; Zoph et al., 2017; Real et al., 2018; Liu et al., 2017; Cai et al., 2018; Elsken et al., 2018) automates this choice of network architecture.”
Neural Architecture Search with Reinforce and Masked Attention Autoregressive Density Estimators (2020, background): “…al., 2018; Ma et al., 2019; White et al., 2019), evolutionary learning (Real et al., 2019; Liu et al., 2017; Real et al., 2017; Xie & Yuille, 2017; Elsken et al., 2018), and gradient based methods (Liu et al., 2018; Luo et al., 2018; Shaw et al., 2019), with random search widely regarded as a…”
Towards Reproducible Neural Architecture and Hyperparameter Search (2018, background): “…(Snoek et al., 2012; Hutter et al., 2011; Bergstra et al., 2011; Hazan et al., 2018; Li et al., 2017) and neural architecture search (NAS) (Baker et al., 2017; Zoph and Le, 2017; Esteban et al., 2017; Elsken et al., 2018) that tries to automate this process by casting it as an optimization problem.”
Learnable Embedding Space for Efficient Neural Architecture Compression (2019, background): “Readers can refer to Elsken et al. (2018b) for a more complete literature review of NAS.”
Fast and Practical Neural Architecture Search (2019, methodology): “In NAS, candidate networks are selected via reinforcement learning [39, 2, 40, 36, 20, 29] or evolutionary schemes [32, 22, 21, 16, 5].”
MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning (2018, methodology): “Pareto-NASH (Thomas Elsken and Hutter, 2018) and Nemo (Ye-Hoon Kim and Seo, 2017) used evolutionary algorithms to search under multiple objectives.”