Micro-Differential Evolution: Diversity Enhancement and Comparative Study
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
Evolutionary algorithms (EAs), such as the differential evolution (DE) algorithm, suffer\nfrom high computational time due to large population size and nature of evaluation, to\nmention two major reasons. The micro-EAs employ a very small population size, which\ncan converge to a reasonable solution quicker; while they are vulnerable to premature\nconvergence as well as high risk of stagnation. One approach to overcome the stagnation\nproblem is increasing the diversity of the population. In this thesis, a micro-differential\nevolution algorithm with vectorized random mutation factor (MDEVM) is proposed, which\nutilizes the small size population benefit while preventing stagnation through diversification\nof the population. The following contributions are conducted related to the micro-DE\n(MDE) algorithms in this thesis: providing Monte-Carlo-based simulations for the proposed\nvectorized random mutation factor (VRMF) method; proposing mutation schemes\nfor DE algorithm with populations sizes less than four; comprehensive comparative simulations\nand analysis on performance of the MDE algorithms over variant mutation schemes,\npopulation sizes, problem types (i.e. uni-modal, multi-modal, and composite), problem\ndimensionalities, mutation factor ranges, and population diversity analysis in stagnation\nand trapping in local optimum schemes. The comparative studies are conducted on the\n28 benchmark functions provided at the IEEE congress on evolutionary computation 2013\n(CEC-2013) and comprehensive analyses are provided. Experimental results demonstrate\nhigh performance and convergence speed of the proposed MDEVM algorithm over variant\ntypes of functions.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.018 |
| Research integrity | 0.000 | 0.002 |
| 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