# Wasserstein Speed-Limit Controller

- ID: 2780
- Canonical URL: https://synthcore.org/idea/2780/wasserstein-speed-limit-controller
- API JSON: https://synthcore.org/api/idea/2780.json
- API Markdown: https://synthcore.org/api/idea/2780.md
- Verification status: failed_benchmark
- Source: [arXiv:2608.27938](https://arxiv.org/abs/2608.27938)
- Category: dynamics
- Solves: stability, speedup, sample-efficiency
- ML areas: optimizer, training-dynamics, scheduler
- Math tags: stochastic-processes, optimal-transport, dynamical-systems, control-theory
- Ratings: usefulness 7/10; difficulty 5/10; novelty 7/10

## Idea description

Wrap stochastic optimization or iterative neural inference in a controller that measures how far the state distribution moves during each interval and compares this motion with the available noise-dependent entropy-production budget. The controller increases the learning rate or reduces inference steps only while the trajectory remains inside the predicted speed-limit region, preventing fast jumps that cause accuracy collapse.

## Mathematical statement

Let p_t(x) be the distribution of network states x, J_t(x) the probability current, v_t(x)=J_t(x)/p_t(x) the probability-flow velocity, D=μ k_B T the diffusion coefficient, and σ_t the entropy-production rate divided by k_B. The continuity equation is ∂_t p_t+∇·(p_t v_t)=0. The Wasserstein action bound implies W_2(p_0,p_τ)^2≤D τ Σ, where Σ=∫_0^τ σ_t dt. Therefore any protocol transporting the distribution over Wasserstein distance W_2 in time τ must satisfy τ≥W_2^2/(DΣ). In a neural implementation, p_t is the empirical distribution of parameter replicas, hidden states, or stochastic predictions; W_2 and Σ are estimated from minibatch samples and consecutive updates.

## Key formulas

- $$\dot{x}=\mu f_\theta(x,t)+\sqrt{2\mu k_{\rm B}T_t}\,\xi(t),\qquad D_t=\mu k_{\rm B}T_t$$
- $$W_2^2(p_0,p_\tau)\leq D\,\tau\,\Sigma,\qquad \Sigma=\int_0^\tau\sigma_t\,dt$$
- $$\sigma_t=\frac{1}{D}\int p_t(x)\left\|\frac{J_t(x)}{p_t(x)}\right\|^2dx,\qquad \tau_{\min}=\frac{W_2^2(p_0,p_\tau)}{D\Sigma}$$
- $$\eta_{t+1}=\eta_t\,\operatorname{clip}\left[\left(\frac{\widehat W_{2,t}^2}{D_t\Delta t\,\widehat\Sigma_t}\right)^\alpha,\frac{\eta_{\min}}{\eta_t},\frac{\eta_{\max}}{\eta_t}\right]$$

## Implementation notes

Integrate the controller into stochastic gradient descent, SGLD, or a diffusion sampler. For an optimizer experiment, maintain K parameter replicas and update each replica with θ_{t+1}^{(k)}=θ_t^{(k)}−η_t g_t^{(k)}+sqrt(2η_t T_t) z_t^{(k)}, where g_t^{(k)} is the minibatch gradient, T_t is an injected temperature, and z_t^{(k)} is standard Gaussian noise. Every m updates, collect replica states before and after the interval. Estimate W_2 with sliced Wasserstein distance using 32 random projections, and estimate the current velocity using v_k=(x_{t+1}^{(k)}−x_t^{(k)})/Δt. Estimate σ_t by the average squared velocity divided by D_t=μ k_B T_t, using an exponential moving average to reduce noise. Compute r=Ŵ_2^2/(D_t Δt Σ̂_t). If r approaches or exceeds one, reduce η or increase the allowed number of steps; if r is well below one and validation accuracy is stable, cautiously increase η. Known quantities are the injected noise and D_t; Wasserstein displacement, velocity, and entropy production are empirical estimates. The first cheap experiment should use a two-layer MLP on MNIST or Fashion-MNIST with 32 replicas, comparing Adam, fixed-step SGLD, and the controller at matched final accuracy. Plot r, loss, accuracy, and replica displacement. The falsifiable prediction is that stable high-accuracy intervals satisfy r≤1 up to estimation error, while deliberately increasing η creates persistent r>1 before divergence or accuracy collapse. The measured critical learning rate should predict the collapse boundary within 20%.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: harms
- Verdict: Built a replica-based SGLD Wasserstein controller and a toy translating-distribution verification. The bound prediction was confirmed: the dimension-corrected sliced-Wasserstein/action ratio had median 1.00, with worst relative error 28.2%; displacement scaling versus speed²·time² ranged from 0.72 to 1.25. In the quadratic stability sweep, the predicted fixed-step boundary eta=0.5 was observed: baseline diverged at eta=0.55 and 0.70, while the controller reduced eta and remained finite, although it sometimes hurt already-stable low-eta runs.

### Mechanism check

- Verdict: Built a replica-based SGLD Wasserstein controller and a toy translating-distribution verification. The bound prediction was confirmed: the dimension-corrected sliced-Wasserstein/action ratio had median 1.00, with worst relative error 28.2%; displacement scaling versus speed²·time² ranged from 0.72 to 1.25. In the quadratic stability sweep, the predicted fixed-step boundary eta=0.5 was observed: baseline diverged at eta=0.55 and 0.70, while the controller reduced eta and remained finite, although it sometimes hurt already-stable low-eta runs.
- Confidence: 7/10
- Limitations: No MNIST/MLP experiment, wall-clock speed, or matched-FLOP study was performed. The dimension-corrected sliced-Wasserstein quantity is an estimator/proxy rather than an exact full W2 distance, and the optimizer test used a quadratic objective with injected noise rather than a realistic neural-network training workload.

### 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

- [bench_report.json](https://synthcore.org/code/1095/bench_report.json)
- [report.md](https://synthcore.org/code/1095/report.md)
- [report_bench_2026-09-02T005743.md](https://synthcore.org/code/1095/report_bench_2026-09-02T005743.md)
- [results.json](https://synthcore.org/code/1095/results.json)
- [stage2_bench.py](https://synthcore.org/code/1095/stage2_bench.py)
- [wasserstein_controller.py](https://synthcore.org/code/1095/wasserstein_controller.py)
- [Download all files as ZIP](https://synthcore.org/download/1095)

## Disclaimer

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