{"work":{"id":"31cb83e2-3381-4fe6-b408-69cdfeebfb7e","openalex_id":null,"doi":null,"arxiv_id":"1802.03268","raw_key":null,"title":"Efficient Neural Architecture Search via Parameter Sharing","authors":null,"authors_text":null,"year":2018,"venue":"cs.LG","abstract":"We propose Efficient Neural Architecture Search (ENAS), a fast and inexpensive approach for automatic model design. In ENAS, a controller learns to discover neural network architectures by searching for an optimal subgraph within a large computational graph. The controller is trained with policy gradient to select a subgraph that maximizes the expected reward on the validation set. Meanwhile the model corresponding to the selected subgraph is trained to minimize a canonical cross entropy loss. Thanks to parameter sharing between child models, ENAS is fast: it delivers strong empirical performances using much fewer GPU-hours than all existing automatic model design approaches, and notably, 1000x less expensive than standard Neural Architecture Search. On the Penn Treebank dataset, ENAS discovers a novel architecture that achieves a test perplexity of 55.8, establishing a new state-of-the-art among all methods without post-training processing. On the CIFAR-10 dataset, ENAS designs novel architectures that achieve a test error of 2.89%, which is on par with NASNet (Zoph et al., 2018), whose test error is 2.65%.","external_url":"https://arxiv.org/abs/1802.03268","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T19:26:09.759496+00:00","pith_arxiv_id":"1802.03268","created_at":"2026-05-20T20:29:00.001586+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Efficient Neural Architecture Search via Parameter Sharing","render_title":"Efficient Neural Architecture Search via Parameter Sharing"},"hub":{"state":{"work_id":"31cb83e2-3381-4fe6-b408-69cdfeebfb7e","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":11,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2019-06-20T22:08:51+00:00","last_pith_cited_at":"2026-05-15T02:44:25+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-12T03:59:28.650533+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":1}],"polarity_counts":[{"context_polarity":"background","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}