A surrogate model assisted (1+1)-ES with increased exploitation of the model
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Surrogate models in black-box optimization can be exploited to different degrees. At one end of the spectrum, they can be used to provide inexpensive but inaccurate assessments of the quality of candidate solutions generated by the black-box optimization algorithm. At the other end, optimization of the surrogate model function can be used in the process of generating those candidate solutions themselves. The latter approach more fully exploits the model, but may be more susceptible to systematic model error. This paper examines the effect of the degree of exploitation of the surrogate model in the context of a simple (1 + 1)-ES. First, we analytically derive the potential gain from more fully exploiting surrogate models by using a spherically symmetric test function and a simple model for the error resulting from the use of surrogate models. We then observe the effects of increased exploitation in an evolution strategy employing Gaussian process surrogate models applied to a range of test problems. We find that the gain resulting from more fully exploiting surrogate models can be considerable.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it