# Decision-Oriented Optimum Preservation

- ID: 2711
- Canonical URL: https://synthcore.org/idea/2711/decision-oriented-optimum-preservation
- API JSON: https://synthcore.org/api/idea/2711.json
- API Markdown: https://synthcore.org/api/idea/2711.md
- Verification status: failed_benchmark
- Source: [arXiv:2608.23885](https://arxiv.org/abs/2608.23885)
- Category: training
- Solves: accuracy, stability, generalization
- ML areas: optimizer, loss, world-model, training-dynamics
- Math tags: optimization, dynamical-systems, control-theory, statistics
- Ratings: usefulness 8/10; difficulty 6/10; novelty 7/10

## Idea description

Train a neural dynamical surrogate not only to reproduce measured trajectories, but also to reproduce the plant's economically optimal decision and objective value. Add a differentiable decision loss obtained by solving the surrogate's inner optimization problem, and reject models that fit observations while producing extra local optima or a shifted optimum.

## Mathematical statement

Let $f_{\theta}$ be a learned process model, $u\in\mathcal U$ the vector of operating decisions, $x_{\theta}(u)$ the predicted steady state or rollout, and $J_{\theta}(u)=c(x_{\theta}(u),u)$ the predicted economic objective to minimize. Let $u^\star$ and $J^\star$ be the trusted plant optimum from a benchmark or high-fidelity simulator. In addition to trajectory loss $L_{\mathrm{data}}(\theta)$, minimize $L_{\mathrm{dec}}(\theta)=\|u_{\theta}^\star-u^\star\|_{W_u}^2+\alpha|J_{\theta}(u_{\theta}^\star)-J^\star|^2$, where $u_{\theta}^\star=\arg\min_{u\in\mathcal U}J_{\theta}(u)$ and $W_u\succeq0$ weights decision coordinates. A local optimum must satisfy $\nabla_uJ_{\theta}(u)=0$ and $\nabla_u^2J_{\theta}(u)\succeq0$. The mechanism predicts that trajectory-equivalent models can have substantially different $u_{\theta}^\star$; decision loss removes this non-identifiability in directions relevant to control.

## Key formulas

- $$J_{\theta}(u)=c(x_{\theta}(u),u),\qquad u_{\theta}^{\star}=\arg\min_{u\in\mathcal U}J_{\theta}(u),$$
- $$L(\theta)=L_{\mathrm{data}}(\theta)+\lambda_u\|u_{\theta}^{\star}-u^{\star}\|_{W_u}^{2}+\lambda_J\left|J_{\theta}(u_{\theta}^{\star})-J^{\star}\right|^{2},$$
- $$\nabla_uJ_{\theta}(u_{\theta}^{\star})=0,\qquad \lambda_{\min}\!\left(\nabla_u^2J_{\theta}(u_{\theta}^{\star})\right)>0\ \text{for a strict local minimum}.$$

## Implementation notes

Integrate this at the surrogate-model training level. Use an MLP or neural ODE to predict the state trajectory or steady state from decision vector $u$, then compute the economic objective $J_{\theta}(u)$ using the same differentiable cost and constraint code used by the real optimizer. For every minibatch or every $K$ training steps, solve the inner problem with projected L-BFGS, SQP, or differentiable unrolled gradient descent from several initial points. Pseudocode is: (1) predict $x_{\theta}(u)$ on measured data and compute $L_{\mathrm{data}}$; (2) initialize $M$ decision vectors; (3) repeat $u_m\leftarrow\Pi_{\mathcal U}[u_m-\rho\nabla_uJ_{\theta}(u_m)]$ for $T$ steps; (4) select the lowest feasible objective as $u_{\theta}^{\star}$; (5) backpropagate $L_{\mathrm{data}}+\lambda_u\|u_{\theta}^{\star}-u^\star\|^2+\lambda_J|J_{\theta}(u_{\theta}^{\star})-J^\star|^2$. The paper supplies the failure mechanism and the decision benchmark; the plant optimum, feasible set, and cost are supplied by the application, while gradients and Hessians are computed by autodiff and the number of optima is estimated by multistart. First experiment: fit a neural ODE on synthetic nonlinear process data where the true objective has one known optimum, compare MSE-only training with the added decision loss, and run 100 multistart optimizations. The quantitative prediction is that MSE-only models will sometimes have several local minima and a nonzero optimum displacement, while decision-aware training should reduce $\|u_{\theta}^{\star}-u^\star\|$ and the number of distinct converged optima; measure success as at least a 50% reduction in optimum displacement and no extra minima in the well-conditioned benchmark.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: harms
- Verdict: Built a differentiable surrogate with unrolled projected inner optimization and decision loss, plus fixed-seed math sweeps. The quadratic inner-loop stability boundary was confirmed at rho=2/H: predicted 0.5405, with contraction at 0.50 and divergence at 0.55. Objective perturbations produced extra minima as epsilon increased, and decision-aware training reduced optimum displacement from 0.40495 to 0.01505 (96.3%) with nearly unchanged data MSE. The mechanism manifested, but the stronger claim about removing extra minima was not established because the simple multistart gradient-flow count produced flat-region artifacts.

### Mechanism check

- Verdict: Built a differentiable surrogate with unrolled projected inner optimization and decision loss, plus fixed-seed math sweeps. The quadratic inner-loop stability boundary was confirmed at rho=2/H: predicted 0.5405, with contraction at 0.50 and divergence at 0.55. Objective perturbations produced extra minima as epsilon increased, and decision-aware training reduced optimum displacement from 0.40495 to 0.01505 (96.3%) with nearly unchanged data MSE. The mechanism manifested, but the stronger claim about removing extra minima was not established because the simple multistart gradient-flow count produced flat-region artifacts.
- Confidence: 8/10
- Limitations: Only a one-dimensional synthetic steady-state surrogate was tested; no neural ODE, constraints beyond box projection, noisy trajectories, multiple decision dimensions, computational/FLOP comparison, or robust Hessian-filtered/local-root basin counting was performed. The simple multistart gradient-flow endpoint counts should not be interpreted as distinct local-minimum counts.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.0081
- Paired wins: 0/8
- Benchmark verdict: idea worse (significant)

## Artifacts

- [REPORT.md](https://synthcore.org/code/1029/REPORT.md)
- [bench_report.json](https://synthcore.org/code/1029/bench_report.json)
- [experiment.py](https://synthcore.org/code/1029/experiment.py)
- [report.md](https://synthcore.org/code/1029/report.md)
- [report_bench_2026-09-01T185404.md](https://synthcore.org/code/1029/report_bench_2026-09-01T185404.md)
- [results.json](https://synthcore.org/code/1029/results.json)
- [stage2_bench.py](https://synthcore.org/code/1029/stage2_bench.py)
- [Download all files as ZIP](https://synthcore.org/download/1029)

## Disclaimer

AI-generated research hypothesis, automatically tested. Not peer-reviewed.