# Tropical support-restricted PINN

- ID: 303
- Canonical URL: https://synthcore.org/idea/303/tropical-support-restricted-pinn
- API JSON: https://synthcore.org/api/idea/303.json
- API Markdown: https://synthcore.org/api/idea/303.md
- Verification status: beats_baseline
- Source: [arXiv:2607.00237](https://arxiv.org/abs/2607.00237)
- Category: architecture
- Solves: accuracy, stability, speedup
- ML areas: mlp, loss, initialization
- Math tags: algebra, geometry, computation
- Ratings: usefulness 6/10; difficulty 5/10; novelty 8/10

## Idea description

Represent the PINN solution in a restricted polynomial or Taylor basis whose exponent set is supplied by tropical support analysis, instead of asking an MLP to discover the local series structure from scratch. The restriction removes coefficients that cannot occur in the formal solution, reducing trainable degrees of freedom and preventing spurious low-order or singular terms.

## Mathematical statement

The paper defines the Boolean semiring \(\mathbb{B}=\{0_{\mathbb{B}}<1_{\mathbb{B}}\}\), with Boolean addition \(x+y=\max\{x,y\}\), so addition records whether a term is present. For a formal series \(\Phi(t)=\sum_{i=0}^{\infty}a_i t^i\in\mathbb{C}[[t]]\), its tropicalization or support is \(\operatorname{supp}(\Phi)=\sum_i v_0(a_i)t^i\), where \(v_0(0)=0_{\mathbb{B}}\) and \(v_0(a)=1_{\mathbb{B}}\) for \(a\neq0\). Its order is \(\operatorname{ord}(\Phi)=\min\{i:a_i\neq0\}\), with \(\operatorname{ord}(0)=\infty\). Let \(A\subseteq\{0,\ldots,K\}\) be the admissible exponent set obtained by tropicalizing the differential-equation residual and retaining exponents compatible with the formal solution; define the restricted ansatz \(u_\theta(t)=\sum_{i\in A}c_i(\theta)t^i\). The mathematical asset is structural sparsity: coefficients outside \(A\) are exactly zero by construction, and the smallest active exponent is controlled by the order constraint rather than learned through a badly conditioned residual loss.

## Key formulas

- $$\mathbb{B}=\{0_{\mathbb{B}}<1_{\mathbb{B}}\},\qquad x+y:=\max\{x,y\},\qquad v_0(0)=0_{\mathbb{B}},\quad v_0(a)=1_{\mathbb{B}}\ \text{for }a\neq0.$$$
- $$\operatorname{supp}\!\left(\Phi\right)=\operatorname{supp}\!\left(\sum_{i=0}^{\infty}a_i t^i\right)=\sum_{i=0}^{\infty}v_0(a_i)t^i,\qquad \operatorname{ord}(\Phi)=\min\{i:a_i\neq0\},\quad \operatorname{ord}(0)=\infty.$$$
- $$u_\theta(t)=\sum_{i\in A}c_i(\theta)t^i,\qquad c_i(\theta)=0\ \text{for }i\notin A,\qquad \operatorname{ord}(u_\theta)=\min\{i\in A:c_i(\theta)\neq0\}.$$$
- $$\mathcal{L}(\theta)=\frac{1}{N}\sum_{n=1}^{N}\left|\mathcal{D}[u_\theta](t_n)-f(t_n)\right|^2+\lambda\left|u_\theta(0)-u_0\right|^2.$$$

## Implementation notes

Integrate this at the PINN output layer, not inside the residual network. First choose a local coordinate \(t\), such as time for Van der Pol or a spatial coordinate near a boundary or shock for Burgers, and a truncation order \(K\). Construct the candidate basis \(\{t^0,\ldots,t^K\}\). From the polynomial differential equation, enumerate candidate formal-series coefficients: initialize a Boolean support mask \(s_i=1\), substitute \(u=\sum_{i=0}^{K}c_i t^i\) into the differential operator, apply derivative shifts \(t^i\mapsto i t^{i-1}\), and apply polynomial products by coefficient convolution. Use the resulting coefficient equations to identify exponents whose coefficients are forced to zero; define \(A=\{i:s_i=1\}\) before training. Use an MLP \(h_\theta(t)\in\mathbb{R}^{|A|}\) and map its outputs to \(u_\theta(t)=\sum_{j=1}^{|A|}h_{\theta,j}(t)t^{A_j}\). A simpler first implementation uses one trainable coefficient per allowed exponent, while a nonlinear coefficient head can be tested afterward. Compute derivatives analytically or with autodiff and minimize the PDE residual and initial or boundary loss in the displayed objective. Enforce a prescribed order by excluding all exponents below the required \(m\), or initialize the first active coefficient separately when it must be nonzero. The paper supplies the Boolean support and order machinery; empirical estimation is only needed when symbolic elimination is too expensive. Begin with a two-layer tanh PINN on one-dimensional Van der Pol and Burgers, using \(K=20\), and compare a dense basis with the tropical mask at equal hidden width and collocation count. Measure residual loss versus optimizer steps, final relative solution error, number of stalled runs, and error near stiff or singular regions. The hypothesis is supported if the masked model reaches a fixed error in fewer steps, has lower run-to-run variance, or achieves lower local error with equal FLOPs.

## Verification

- Status: beats_baseline
- Mechanism evidence: yes
- Mechanism confirmed: yes
- Practical verdict: helps
- Verdict: Built a coefficient-based tropical support-restricted PINN for u'=1+u^2, u(0)=0, using the formally derived odd-power support of tan(t). The recurrence check exactly produced zero even coefficients, and across three fixed seeds the restricted model used 8 rather than 16 coefficients, reduced mean residual loss from 4.55e-6 to 8.42e-9, and reduced relative solution error from 2.25e-4 to 7.86e-6 at equal optimization steps. This is a clear toy-system signal for the claimed structural-sparsity effect, but it is not evidence yet for general PDEs or MLP coefficient heads.

### Mechanism check

- Verdict: Built a coefficient-based tropical support-restricted PINN for u'=1+u^2, u(0)=0, using the formally derived odd-power support of tan(t). The recurrence check exactly produced zero even coefficients, and across three fixed seeds the restricted model used 8 rather than 16 coefficients, reduced mean residual loss from 4.55e-6 to 8.42e-9, and reduced relative solution error from 2.25e-4 to 7.86e-6 at equal optimization steps. This is a clear toy-system signal for the claimed structural-sparsity effect, but it is not evidence yet for general PDEs or MLP coefficient heads.
- Confidence: 8/10
- Limitations: Only a one-dimensional Riccati ODE on t in [0,1] was tested, with one trainable scalar coefficient per basis exponent rather than the proposed nonlinear MLP coefficient head. No Van der Pol, Burgers, wall-clock speed, FLOP-normalized comparison, or broader support-analysis implementation was tested.

### Practical benchmark

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

## Artifacts

- [bench_report.json](https://synthcore.org/code/1262/bench_report.json)
- [report.md](https://synthcore.org/code/1262/report.md)
- [report_bench_2026-09-03T232251.md](https://synthcore.org/code/1262/report_bench_2026-09-03T232251.md)
- [results.json](https://synthcore.org/code/1262/results.json)
- [run_experiment.py](https://synthcore.org/code/1262/run_experiment.py)
- [stage2_bench.py](https://synthcore.org/code/1262/stage2_bench.py)
- [tropical_bvp_track.py](https://synthcore.org/code/1262/tropical_bvp_track.py)
- [Download all files as ZIP](https://synthcore.org/download/1262)

## Disclaimer

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