Mutation Operators for Merge Genome Evolution

Mutation operators introduce variation into merge genomes during the EMEP evolutionary loop. Each operator targets a specific genome field and applies a bounded perturbation. This page specifies the available operators, their mechanics, rate scheduling, and validation constraints.

Mutation Flowchart

Alpha Jitter

Perturbs global alpha coefficients by adding Gaussian noise. The noise scale is proportional to the current alpha value to preserve relative weighting.

alpha_i' = alpha_i + N(0, sigma * alpha_i)
alpha_i' = clip(alpha_i', 0, 1)
alpha' = normalize(alpha')

Sigma is configurable, default 0.1. After perturbation, coefficients are re-normalized to sum to 1.0. If any coefficient falls below a minimum threshold (default 0.01), it is set to zero and the remainder re-normalized.

Per-Layer Perturbation

Applies alpha jitter independently to each layer range defined in per_layer_alpha. This allows the genome to evolve heterogeneous blending across the model depth. The same Gaussian noise model applies per layer range. If per_layer_alpha is absent, the operator has a configurable probability of creating it by copying global alpha into layer-specific ranges.

Strategy Switch

Replaces the merge method with another supported strategy. The switch is random but weighted by historical success rates. Methods with higher average fitness in the current experiment receive higher switch probability. Supported transitions:

From	To	Notes
TIES	DARE	Both use density, transition preserves density value
DARE	TIES	Density value remains valid
SLERP	Task Arithmetic	Alpha becomes task vector scaling
Task Arithmetic	SLERP	Task vectors discarded, alpha restored
Any	Franken-Merge	Requires layer routing initialization

Density Adjustment

Modifies the density parameter for TIES (Yadav et al. 2023) and DARE (Yu et al. 2023) merges. Adjustment is multiplicative:

density' = density * (1 + N(0, sigma_density))
density' = clip(density', min_density, 1.0)

Default sigma_density is 0.15. Minimum density is 0.2. Values below 0.2 are rejected as too sparse for stable merges.

Rate and Schedule

The base mutation rate is 0.1 per gene. EMEP supports two schedules: Static: fixed rate for all generations Adaptive: rate increases when diversity falls, decreases when diversity is high

rate_adaptive = base_rate * (1 + (diversity_target - diversity_current) / diversity_target)
rate_adaptive = clip(rate_adaptive, 0.05, 0.5)

Retry Logic

Invalid mutations are retried up to 3 times with the same operator. If all retries fail, the genome is returned unchanged. Invalid states include:

Alpha coefficients that do not sum to 1.0 after normalization
Density outside valid range
Strategy switch to incompatible parent configuration
Layer routing with gaps or overlaps

Validation

Every mutated genome passes through the same validation rules as manually created genomes. See Genome for the full validation specification.

High mutation rates combined with small population sizes can destabilize the search. If more than 30% of mutations produce invalid genomes, the engine logs a warning and suggests reducing mutation rate or expanding the search space.

Evolution Engine

Evaluation

Tracking & Reproducibility

Mutation Operators for Merge Genome Evolution

Mutation Flowchart

Alpha Jitter

Per-Layer Perturbation

Strategy Switch

Density Adjustment

Rate and Schedule

Retry Logic

Validation

​Mutation Flowchart

​Alpha Jitter

​Per-Layer Perturbation

​Strategy Switch

​Density Adjustment

​Rate and Schedule

​Retry Logic

​Validation

Mutation Flowchart

Alpha Jitter

Per-Layer Perturbation

Strategy Switch

Density Adjustment

Rate and Schedule

Retry Logic

Validation