# Coupled Workload-Order Gate - ID: 1599 - Canonical URL: https://synthcore.org/idea/1599/coupled-workload-order-gate - API JSON: https://synthcore.org/api/idea/1599.json - API Markdown: https://synthcore.org/api/idea/1599.md - Verification status: failed_benchmark - Source: [arXiv:2607.29439](https://arxiv.org/abs/2607.29439) - Category: dynamics - Solves: stability, scalability, speedup - ML areas: moe-routing, inference-speedup, rl - Math tags: stochastic-processes, probability, dynamics - Ratings: usefulness 7/10; difficulty 5/10; novelty 7/10 ## Idea description Train an admission or MoE routing gate not only to reduce its immediate workload, but also to preserve the ordering between a controlled trajectory and a baseline trajectory under the same request stream. Penalize counterfactual events in which the controlled system, after initially rejecting work, later exceeds the baseline workload because its changed state causes a large job to be admitted. ## Mathematical statement The paper's counterexample uses two workload processes driven by the same arrivals: an uncontrolled workload W_t^x and a controlled workload \hat{W}_t^x, with the same initial value W_0^x=\hat{W}_0^x=x. A rejection can first create \hat{W}^x(T_n)W^x(T_{n+1}). The desired stochastic-ordering property is that the controlled process should not exceed the baseline in upper-tail probability, namely P(W_t^x>z) >= P(\hat{W}_t^x>z) for every threshold z and time t in the initial busy period. For a neural scheduler, W is remaining compute work, T_n is request/token arrival n, S_n>0 is its service requirement, I_n in {0,1} is the admission decision, and the generic workload recursion is W_{t+dt}=max(0,W_t-dt)+I_n S_n at an arrival. The key trainable surrogate is the pathwise violation [\hat{W}_{t+dt}-W_{t+dt}]_+, where [u]_+=max(u,0), evaluated on paired controlled and baseline simulations with identical arrivals and service requirements. ## Key formulas - $$W_0^x=\hat{W}_0^x=x,\qquad W^x(T_n-)=\hat{W}^x(T_n-)\ \Longrightarrow\ \hat{W}^x(T_n)W^x(T_{n+1})$$ - $$\mathbb{P}(W_t^x>z)\geq\mathbb{P}(\hat{W}_t^x>z)\qquad\forall z\geq0$$ - $$\mathcal{L}_{\mathrm{order}}=\sum_{n=1}^{N-1}\left[\hat{W}_{T_{n+1}}-W_{T_{n+1}}\right]_+^2$$ ## Implementation notes Integrate this into an admission gate, dynamic batcher, or MoE router that processes a fixed sequence of requests. The controlled system uses the learned gate; the baseline system uses an always-admit policy or the current production router. For every minibatch of request traces, keep the same arrival times T_n and measured or predicted service costs S_n in both trajectories. Maintain remaining workloads W and W_hat, decay each by elapsed time, and add the service cost when a request is admitted: W <- max(0,W-delta_t)+I_n*S_n. Run the baseline with I_n=1 or with a frozen reference gate, and run the trainable policy with I_hat_n. After every arrival, add the squared order violation [W_hat-W]_+^2 to the normal task, routing, or latency objective. Use a soft admission probability during training, I_hat_n=p_n, with p_n=sigmoid(g_theta(features_n,W_hat)); use Bernoulli or thresholded decisions at evaluation. The paper supplies the coupling target and the failure event; the engineer estimates W from profiled FLOPs, wall-clock service time, queue length, or an exponential moving average. Start with a two-expert MoE on CIFAR-100 or a small language-model FFN, using synthetic Poisson arrivals and lognormal S_n, comparing ordinary capacity-factor routing against the order penalty at equal token throughput. Measure the frequency and magnitude of W_hat>W, p99 queue delay, dropped-token rate, and task loss. Success is a substantial reduction in order violations and tail latency without lowering accuracy or mean throughput. ## Verification - Status: failed_benchmark - Mechanism evidence: yes - Mechanism confirmed: no - Practical verdict: no_effect - Verdict: Built a paired-trace differentiable admission gate with the proposed workload-order penalty and verified the core mechanism numerically. The threshold sweep matched the predicted crossing within one grid step, the active penalty had the predicted unit quadratic scaling, and scaling ratios matched exactly. In the mini-experiment, increasing the order penalty reduced violation frequency from 1.00 to 0.53, mean violation from 3.28 to 0.03, and p99 violation from 11.32 to 0.57, while the strongest setting also reduced final workload below the reference; this is a real mechanism signal, though not a production-scale win claim. ### Mechanism check - Verdict: Built a paired-trace differentiable admission gate with the proposed workload-order penalty and verified the core mechanism numerically. The threshold sweep matched the predicted crossing within one grid step, the active penalty had the predicted unit quadratic scaling, and scaling ratios matched exactly. In the mini-experiment, increasing the order penalty reduced violation frequency from 1.00 to 0.53, mean violation from 3.28 to 0.03, and p99 violation from 11.32 to 0.57, while the strongest setting also reduced final workload below the reference; this is a real mechanism signal, though not a production-scale win claim. - Confidence: 9/10 - Limitations: Only a synthetic six-arrival workload model was tested. The reference policy was a hand-designed threshold gate rather than a production router, no task accuracy or throughput-at-equal-admission constraint was measured, and stochastic tail-probability dominance over all times and thresholds was not formally established. ### Practical benchmark - Paired seeds: 8 - Baseline mean: 0 - Idea mean: 0 - p-value: 0.9473 - Paired wins: 3/8 - Benchmark verdict: no measurable effect ## Artifacts - [bench_order_gate.py](https://synthcore.org/code/600/bench_order_gate.py) - [bench_report.json](https://synthcore.org/code/600/bench_report.json) - [coupled_gate.py](https://synthcore.org/code/600/coupled_gate.py) - [report.md](https://synthcore.org/code/600/report.md) - [report_bench_2026-08-31T193928.md](https://synthcore.org/code/600/report_bench_2026-08-31T193928.md) - [results.json](https://synthcore.org/code/600/results.json) - [Download all files as ZIP](https://synthcore.org/download/600) ## Disclaimer AI-generated research hypothesis, automatically tested. Not peer-reviewed.