Papers › EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization

EMQ: Evolving Training-free Proxies for Automated Mixed Precision Quantization

20 Jul 2023ICCV 2023 1arXiv:2307.10554archive 2025-07-28

Peijie Dong, Lujun Li, Zimian Wei, Xin Niu, Zhiliang Tian, Hengyue Pan

Mixed-Precision Quantization (MQ) can achieve a competitive accuracy-complexity trade-off for models. Conventional training-based search methods require time-consuming candidate training to search optimized per-layer bit-width configurations in MQ. Recently, some training-free approaches have presented various MQ proxies and significantly improve search efficiency. However, the correlation between these proxies and quantization accuracy is poorly understood. To address the gap, we first build the MQ-Bench-101, which involves different bit configurations and quantization results. Then, we observe that the existing training-free proxies perform weak correlations on the MQ-Bench-101. To efficiently seek superior proxies, we develop an automatic search of proxies framework for MQ via evolving algorithms. In particular, we devise an elaborate search space involving the existing proxies and perform an evolution search to discover the best correlated MQ proxy. We proposed a diversity-prompting selection strategy and compatibility screening protocol to avoid premature convergence and improve search efficiency. In this way, our Evolving proxies for Mixed-precision Quantization (EMQ) framework allows the auto-generation of proxies without heavy tuning and expert knowledge. Extensive experiments on ImageNet with various ResNet and MobileNet families demonstrate that our EMQ obtains superior performance than state-of-the-art mixed-precision methods at a significantly reduced cost. The code will be released.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 19 code samples harvested from 1 repository linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 19 samples from 1 repository, 7 ran (6 with no instrument failure; 1 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

lilujunai/emq-series officialmentioned in paperpytorchSyntology: 19 samples, 7 ran (1 instrument-failed) · 12 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

19 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · violated contract
1ran · our draft was wrong
4ran
12unverified

Licence: 0 of the 19 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lilujunai/emq-series. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

lilujunai/emq-series official repository 19 samples, 7 ran (1 instrument-failed) · 12 unverified
BasicBlock in 126 papers
census: 6 implementations from 6 papers, 5 distinct outputs on one shared input
emq/predictor/pruners/measures/qe_score.py ran Apache-2.0 (permissive) · cc18b58d20c93dfd · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
Bottleneck in 98 papers emq/predictor/pruners/measures/qe_score.py ran Apache-2.0 (permissive) · df082992e7ba0798 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
InvertedResidual in 9 papers emq/predictor/pruners/measures/qe_score.py ran fingerprinted Apache-2.0 (permissive) · 491ef5b3386ab4b7 · report fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24
StraightThrough emq/predictor/pruners/measures/qe_score.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 78941fdc9f230be6 · report fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-22
_fold_bn emq/predictor/pruners/measures/qe_score.py ran · our draft was wrong Apache-2.0 (permissive) · 140878966d2be929 · report fixture: signature conv_module:callable/0/?, bn_module:callable/0/? · returned tuple · level recorded 2026-09-22
is_absorbing in 6 papers emq/predictor/pruners/measures/qe_score.py ran · violated contract Apache-2.0 (permissive) · 21b513cf47621143 · report fixture: signature m:callable/0/? · returned bool · level recorded 2026-09-22
is_bn in 9 papers emq/predictor/pruners/measures/qe_score.py ran · violated contract Apache-2.0 (permissive) · 39d986a037856c1d · report fixture: signature m:callable/0/? · returned bool · level recorded 2026-09-22
BaseQuantBlock emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · 819d5ef809058894 · report
ComputeMadnasScore emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · 2028d48de55aba38 · report
QuantBasicBlock emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · affd5495e8ec4d0e · report
QuantBottleneck emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · 88f5b8c6e343729d · report
QuantInvertedResidual emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · 47fc8538a2628e4c · report
QuantModel emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · 4895c833da6c7c80 · report
QuantModule emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · 0d7bbdf53ee6e6db · report
UniformAffineQuantizer in 11 papers emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · d4a79d5ee2cd4666 · report
compute_qe_score emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · ac0703e88e81917a · report
convert_qnn emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · ced4515523449616 · report
fold_bn_into_conv emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · 529664956b8dab9a · report
search_fold_and_remove_bn emq/predictor/pruners/measures/qe_score.py unverified Apache-2.0 (permissive) · de6383d946b71e09 · report

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for EMQ (graph method: EMQ). 24 bricks; individually on a fixture: 12 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 2 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 12 unverified. The assembly has not been run end-to-end.

  1. compute_qe_score entry · level 0 · unverified · ac0703e88e81917a
  2. ComputeMadnasScore helper · level 0 · unverified · 2028d48de55aba38
  3. convert_qnn helper · level 0 · unverified · ced4515523449616
  4. measure helper · level 1 · ran · our draft was wrong · bdba060dbdcaeb6d
  5. QuantBasicBlock helper · level 0 · unverified · affd5495e8ec4d0e
  6. QuantBottleneck helper · level 0 · unverified · 88f5b8c6e343729d
  7. QuantModel helper · level 0 · unverified · 4895c833da6c7c80
  8. BaseQuantBlock helper · level 0 · unverified · 819d5ef809058894
  9. BasicBlock helper · level 1 · ran · cc18b58d20c93dfd
  10. QuantModule helper · level 0 · unverified · 0d7bbdf53ee6e6db
  11. Bottleneck helper · level 1 · ran · df082992e7ba0798
  12. StraightThrough helper · level 1 · ran · 78941fdc9f230be6
  13. search_fold_and_remove_bn helper · level 0 · unverified · de6383d946b71e09
  14. UniformAffineQuantizer helper · level 0 · unverified · d4a79d5ee2cd4666
  15. conv3x3 helper · level 1 · ran · our draft was wrong · 160bb14bd76201b4
  16. conv1x1 helper · level 1 · ran · our draft was wrong · d9def42110729a85
  17. fold_bn_into_conv helper · level 0 · unverified · 529664956b8dab9a
  18. is_absorbing helper · level 1 · ran · violated contract · 21b513cf47621143
  19. is_bn helper · level 1 · ran · violated contract · 39d986a037856c1d
  20. lp_loss helper · level 1 · ran; the contract check could not run · 08c6ea7576220a13
  21. round_ste helper · level 2 · ran · our draft was wrong · 675da8641c602b03
  22. _fold_bn helper · level 1 · ran · our draft was wrong · 140878966d2be929
  23. InvertedResidual helper · level 1 · ran · 491ef5b3386ab4b7
  24. QuantInvertedResidual helper · level 0 · unverified · 47fc8538a2628e4c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2307.10554") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Quantization

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections