E-optimal-ranking (EOR): Design & Fairness

• E-optimal-ranking (EOR) is defined in two contexts: robust simulation-based sampling for nonlinear ODE models and a fairness criterion for group-wise equitable ranking.
• In experiment design, it uses Monte Carlo sampling, sensitivity propagation, and SDP-based selection to improve parameter estimation with measurable error reduction.
• For fair ranking, it employs a group-wise merge algorithm to balance relevance mass across groups, achieving computational efficiency with theoretical fairness guarantees.

E-optimal-ranking (EOR) refers to two distinct formal methodologies in the academic literature: one in simulation-based optimal experiment design for dynamical systems (Ha et al., 10 Nov 2025), and one as a fairness criterion for group-wise equitable ranking under relevance uncertainty (Rastogi et al., 2023). Both approaches, despite sharing a naming convention, address fundamentally different problems—sample point selection for optimal parameter estimation versus unfair burden mitigation in ranked selection processes. Each leverages a ranking or optimization mechanism to realize its underlying criterion, and both introduce practical algorithms with quantified theoretical guarantees and empirical validation.

1. E-optimal-ranking in Simulation-based Optimal Sampling Design

The E-optimal-ranking (EOR) method in systems biology targets robust optimal sampling design for parameter estimation in nonlinear ODE models. Given a dynamical system

$\dot X(t) = f(X(t), \theta), \quad X(t_0) = X_0,$

with observations

$$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$

the traditional design objective is to maximize the smallest eigenvalue $\lambda_{\min}$ of the Fisher information matrix (FIM)

$I(\theta) = \sum_{k=1}^N S_k^\top S_k,$

where $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$ denotes the sensitivity at time $t_k$.

Classical E-optimal design requires a plug-in parameter $\theta$, rendering it sensitive to prior misspecification. The EOR approach circumvents this by integrating over a parameter prior, yielding a ranking-based consensus robust to uncertainty. It proceeds as follows:

• Monte Carlo Sampling: For $j = 1, \ldots, K$, sample $\theta^{(j)}$ uniformly from a parameter box $\Theta$.
• Sensitivity Propagation: For each draw, solve $$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$0 and sensitivity ODEs to obtain $$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$1 for all candidate times $$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$2.
• SDP-based Selection: For each $$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$3, solve the convex semi-definite program

$$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$4

ranking times in descending order by $$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$5.

• Consensus Aggregation: Compute $$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$6, the average rank of each time $$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$7 across all draws.
• Design Extraction: Select the $$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$8 lowest average rank times as the final sample schedule.

A typical implementation uses $$y(t_k) = g(X(t_k)) + w_k, \quad w_k \sim \mathcal{N}(0, \Sigma),$$9 Monte Carlo draws and candidate grids $\lambda_{\min}$0. SDP solvers like CVXPY+MOSEK or Gurobi, warm-starting, and high-order ODE integrators are standard.

2. Statistical Properties and Numerical Performance in Systems Biology

EOR's statistical robustness emerges from its use of the empirical prior over $\lambda_{\min}$1, converting parameter uncertainty into sampling design consensus and obviating the need for post-selection bootstrapping or plug-in estimates. The only approximation comes from finite Monte Carlo sampling; stabilization occurs for $\lambda_{\min}$2 in observed practice.

Empirical studies using Lotka-Volterra and three-compartment pharmacokinetic models, with $\lambda_{\min}$3 out of $\lambda_{\min}$4 times selected, show that EOR achieves a mean squared parameter error reduction of approximately 30% compared to both random and plug-in E-optimal selection in the LV model, and matches the best classical E-optimal in the PK model for $\lambda_{\min}$5 simulated datasets. Tukey’s HSD tests at FWER=0.05 confirm statistically significant improvements on LV and parity with the classical method on PK.

Method	LV model mean (std)	3-comp. mean (std)
Random	1.63 (0.61)	1.08 (0.61)
E-optimal	1.76 (0.61)	0.55 (0.27)
EOR	1.22 (0.44)	0.55 (0.26)
At-LSTM	1.27 (0.39)	0.77 (0.50)

Performance gains indicate that EOR can yield a single design robust to parameter realization and at least as efficient as classical approaches.

3. Complexity, Implementation Guidelines, and Limitations

The main computational cost of EOR arises from $\lambda_{\min}$6 folds of sensitivity ODE solving and solution of $\lambda_{\min}$7 SDPs. Each SDP, with naive routines, scales as $\lambda_{\min}$8 per solve, which can become significant if $\lambda_{\min}$9 or parameter dimension $I(\theta) = \sum_{k=1}^N S_k^\top S_k,$0 is large—though sparsity-aware solvers offer practical mitigations.

For grid size $I(\theta) = \sum_{k=1}^N S_k^\top S_k,$1–$I(\theta) = \sum_{k=1}^N S_k^\top S_k,$2 and $I(\theta) = \sum_{k=1}^N S_k^\top S_k,$3, standard computational resources are sufficient. Best practices include:

• Monitoring average rank convergence as a stopping criterion,
• Warm-starting SDPs,
• Using adaptive ODE integrators,
• Selecting sample size $I(\theta) = \sum_{k=1}^N S_k^\top S_k,$4 based on experimental constraints.

A plausible implication is that EOR is tractable and effective for moderate-scale experimental regimes but may be computationally demanding for very large grids or high-dimensional parameter spaces.

4. E-optimal-ranking as a Fairness Criterion in Group-wise Ranking under Uncertainty

In ranking under uncertainty, particularly with relevance-score disparity between groups, EOR is defined as a fairness criterion ensuring that each group’s relevant mass appears at similar rates throughout all ranking prefixes. Let $I(\theta) = \sum_{k=1}^N S_k^\top S_k,$5 candidates split into protected groups $I(\theta) = \sum_{k=1}^N S_k^\top S_k,$6, each with model-based expected relevance $I(\theta) = \sum_{k=1}^N S_k^\top S_k,$7.

The EOR criterion seeks a deterministic ranking $I(\theta) = \sum_{k=1}^N S_k^\top S_k,$8 such that, for all $I(\theta) = \sum_{k=1}^N S_k^\top S_k,$9,

$$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$0

where $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$1 is the cumulative relevance mass from group $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$2 in the first $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$3 slots, and $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$4 achieves perfect group fairness matching a fair lottery.

The corresponding integer program minimizes overall missed-relevance cost while enforcing the EOR fairness constraint for any prefix size $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$5.

5. Algorithmic Realization and Approximation Guarantees in Ranking

Efficient computation of EOR rankings is enabled via a group-wise merge algorithm:

• Independently sort each group’s candidates by $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$6 (local PRP).
• Greedily select the group whose next candidate yields the smallest $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$7 increment when appended to the mixed ranking.
• Continue until $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$8 slots are filled, repairing as needed if a group is exhausted.

This yields $$S_k = \frac{\partial X(t_k; \theta)}{\partial \theta}$$9 runtime for two groups, and $t_k$0 for $t_k$1 groups. The method admits an explicit additive approximation bound: for every prefix $t_k$2, principal cost is within $t_k$3 of the ILP optimum, with $t_k$4 the maximal achieved imbalance and $t_k$5 a function of last-selected $t_k$6's and groupwise normalized scores.

For $t_k$7 groups, the merge generalizes by always picking the group whose addition minimizes the maximal-minimal groupwise coverage gap.

6. Comparative Evaluation in Ranking and Empirical Outcomes

EOR’s fairness-by-mass property stands in contrast to other ranking fairness approaches:

• Probability Ranking Principle (PRP): maximizes expected relevance but ignores groupwise equity, potentially yielding high burden on minority groups.
• Demographic Parity (DP): enforces group count parity in top-$t_k$8 but not coverage of relevant mass, often failing with disparate uncertainty.
• Proportional Rooney Rule (FA*IR): prioritizes headcount constraints for a pre-designated group, without balancing relevance mass.
• Exposure-based Fairness: averages representation across entire ranking, which may be insufficient for finite prefix or practical review scenarios.

Empirical studies on synthetic data, US Census predictions (e.g., Black/White in Alabama, multi-racial in NY), and Amazon product search logs demonstrate that EOR achieves near-zero maximal groupwise burden difference ($t_k$9) and equalizes group outranking costs. Principal performance metrics (recall@k, nDCG) remain competitive with PRP. EOR also proves valuable in audit settings, highlighting disparities in existing deployed rankings where access to ground-truth or calibrated models is available.

7. Synthesis: Distinct Contexts for E-optimal-ranking

The E-optimal-ranking (EOR) nomenclature encapsulates two mathematically rigorous approaches advancing the state-of-the-art in their respective domains:

• In systems biology, EOR transforms plug-in FIM-based optimal experiment design into a robust, simulation-based consensus ranking for sampling, eliminating critical dependence on prior parameter estimates and demonstrating superior empirical performance with quantifiable efficiency/cost trade-offs.
• In machine learning fairness, EOR provides a principled ranking mechanism that equalizes fairness costs across protected groups under disparate uncertainty, is computationally efficient, and offers theoretical guarantees bounding the additional total cost relative to classical, group-agnostic ranking.

The shared foundation is the conversion of an optimality or fairness criterion into a practical, tractable ranking algorithm—either over time points for ODE sampling or candidate orderings for sensitive human/machine decision tasks. The terminology EOR thus serves both as a precise descriptor and a unifying concept for robust and equitable selection under uncertainty.