AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

BLOX: Macro Neural Architecture Search Benchmark and Algorithms

Thomas Chun Pong Chau, Łukasz Dudziak, Hongkai Wen, Nicholas Donald Lane, Mohamed S Abdelfattah

NeurIPS 2022 · Architectures and efficiency › Neural architecture search · approach: Efficient NAS search strategies · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Fine-tune 10 epochs then retrain top models 200 epochs (FT10+FT200) instead of FT200 only, good teacherBlockwise NAS · Bloxaccuracy @ cost=40: 76.90 -> 77.66Improved
Search with only 10 fine-tuning epochs (FT10) instead of 200 (ablation)Blockwise NAS · Bloxaccuracy @ cost=40: 76.90 -> 73.47Hurt
Use bad teacher M5 instead of good teacher M1 with FT10 (ablation)Blockwise NAS · Bloxaccuracy @ cost=40: 73.47 -> 70.67Hurt
Retrain after bad-teacher search using iteratively chosen teacherBlockwise NAS · Bloxaccuracy @ cost=40: 70.67 -> 76.88Improved
Fine-tune with teacher chosen by training from scratch (iter 1)Student models m1-m5 · Bloxaccuracy (%): 74.89 -> 76.35Improved
Second iteration of teacher selection (iter 2, m4 as teacher)Student model m4 · Bloxaccuracy (%): 76.36 -> 76.67Improved
Second iteration of teacher selectionStudent model m1 · Bloxaccuracy (%): 76.35 -> 75.61Hurt
Blockwise NAS with fine-tuning versus conventional BRP-NASDONNA/blockwise · Bloxaccuracy @ cost=40: 76.40 -> 77.66Improved
Regularized evolution versus BRP-NASconventional NAS · Bloxaccuracy @ cost=40: 76.40 -> 76.10Hurt
Remove fine-tuning from DONNA (only block signatures) (ablation)DONNA · Bloxsearch accuracyNo clear effect
Remove fine-tuning from LANA (ablation)LANA · Bloxsearch accuracyHurt
Use bad teacher M5 rather than good teacher M1 for ranking modelsFine-tuning · Bloxrank correlationNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy