Efficient Neural Architecture Search via Parameter Sharing · HackerPapers discussions

Efficient Neural Architecture Search via Parameter Sharing — mentioned by kripke

Fri, 13 Jul 2018 18:55:47 GMT

Not GP, but you are probably looking for the "Neural Architecture Search" series [1] [2] [3]. First one uses something like 1k GPUs for a month, next one is a bit more reasonable, and the last one actually has a reasonable training time, and has comparable performance to DARTS (see ENAS in comparison tables). 1: https://arxiv.org/abs/1611.01578 2: https://arxiv.org/abs/1707.07012 3: https://arxiv.org/abs/1802.03268

Paper and discussion history. A mention is not an endorsement.

Efficient Neural Architecture Search via Parameter Sharing — HN submission

Wed, 14 Feb 2018 20:25:38 GMT

Efficient Neural Architecture Search via Parameter Sharing

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Efficient Neural Architecture Search via Parameter Sharing — HN submission

Mon, 12 Feb 2018 11:46:08 GMT

Efficient Neural Architecture Search via Parameters Sharing

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.