# Multiplicity-balanced symmetric interaction layer

- ID: 2259
- Canonical URL: https://synthcore.org/idea/2259/multiplicity-balanced-symmetric-interaction-layer
- API JSON: https://synthcore.org/api/idea/2259.json
- API Markdown: https://synthcore.org/api/idea/2259.md
- Verification status: mech_ok_no_baseline
- Source: [arXiv:2608.13753](https://arxiv.org/abs/2608.13753)
- Category: architecture
- Solves: memory, stability, accuracy
- ML areas: mlp, architecture, regularization
- Math tags: combinatorics, functional-analysis, inequalities
- Ratings: usefulness 7/10; difficulty 4/10; novelty 7/10

## Idea description

Replace a dense degree-m tensor interaction layer by a symmetric orbit-parameterized layer with one parameter per exponent vector and explicit multinomial scaling. This preserves the contribution of all ordered tensor entries represented by one orbit, while reducing parameter count and avoiding the amplitude distortion of unweighted monomial compression.

## Mathematical statement

For a symmetric m-linear form T on C^d, let alpha=(alpha_1,...,alpha_d) in N^d satisfy |alpha|=sum_j alpha_j=m. All ordered tuples with histogram alpha form a permutation orbit of size N_alpha=m!/prod_j alpha_j!. T_alpha is the common ordered coefficient on that orbit, and x^alpha=prod_j x_j^{alpha_j}. The exact diagonal identity is P(x)=T(x,...,x)=sum_{|alpha|=m}N_alpha T_alpha x^alpha. For the Bohnenblust-Hille exponent q=2m/(m+1), the orbit coefficient quantity is sum_alpha N_alpha|T_alpha|^q. The paper proves an asymptotic complex symmetric norm ratio bounded by 1+C/m for sufficiently large m; the implementation uses the exact multiplicities, not an unknown asymptotic constant. Here N_alpha is a combinatorial multiplicity, T_alpha is the shared ordered-tensor value, and c_alpha=N_alpha T_alpha is the polynomial coefficient.

## Key formulas

- $$N_{\alpha}=\frac{m!}{\prod_{j=1}^{d}\alpha_j!},\qquad P(x)=T(x,\ldots,x)=\sum_{|\alpha|=m}N_{\alpha}T_{\alpha}x^{\alpha},\qquad x^{\alpha}=\prod_{j=1}^{d}x_j^{\alpha_j}.$$
- $$\|T\|_{\mathrm{orbit},q}^{q}=\sum_{|\alpha|=m}N_{\alpha}|T_{\alpha}|^{q},\qquad q=\frac{2m}{m+1}.$$
- $$\frac{\|T\|_{\mathrm{BH}}}{\|P\|_{\infty}}\leq 1+\frac{C}{m}\quad\text{for sufficiently large }m.$$
- $$\widetilde T_{\alpha}=\frac{\theta_{\alpha}}{N_{\alpha}^{1/2}},\qquad P_{\theta}(x)=\sum_{|\alpha|=m}N_{\alpha}^{1/2}\theta_{\alpha}x^{\alpha}.$$

## Implementation notes

Integrate this as a replacement for a dense degree-m symmetric tensor contraction in a polynomial MLP, invariant set encoder, or symmetric feature-interaction block. The input is x in R^d, and the trainable object is one parameter theta_alpha for every exponent vector alpha with |alpha|=m. Precompute the compositions alpha and logN_alpha=lgamma(m+1)-sum_j lgamma(alpha_j+1). Use the variance-balanced feature phi_alpha(x)=exp(0.5*logN_alpha)*x^alpha and output y=sum_alpha theta_alpha phi_alpha(x). Pseudocode: enumerate alpha; compute logN; initialize theta; for each minibatch compute each x^alpha by repeated products or dynamic programming; multiply by exp(0.5 logN); sum theta_alpha*phi_alpha; backpropagate. If coefficient regularization is wanted, add lambda*sum_alpha N_alpha*abs(theta_alpha/sqrt(N_alpha))^q, with q=2m/(m+1). The multiplicities and q are exact; the theorem's constant C is not needed. First compare against an ordered tensor layer, an unweighted orbit layer, and a standard MLP at matched parameter count. Use d=32 and m=4 or 6 on synthetic permutation-invariant regression and a DeepSets classification task. Measure parameters, wall-clock time, activation variance, gradient variance, and validation error. Success is a 3-10x parameter reduction with no accuracy loss and more uniform gradients across monomial supports.

## Verification

- Status: mech_ok_no_baseline
- Mechanism evidence: yes
- Mechanism confirmed: yes
- Practical verdict: inconclusive
- Verdict: Built a compact symmetric orbit interaction experiment with composition enumeration, exact multinomial multiplicities, weighted features, BH orbit norms, and regression comparison. The quantitative predictions were confirmed: parameter reduction matched d^m/C(d+m-1,m), diagonal reconstruction and BH orbit sums had numerical error below 7e-10, and weighted feature second moments scaled by exactly N_alpha. The proposed sqrt(N_alpha) factor preserves ordered-tensor contributions but does not equalize raw activation variance; it amplifies high-multiplicity supports, so the 'balanced' label should be interpreted as coefficient/orbit normalization rather than raw feature-variance balancing.

### Mechanism check

- Verdict: Built a compact symmetric orbit interaction experiment with composition enumeration, exact multinomial multiplicities, weighted features, BH orbit norms, and regression comparison. The quantitative predictions were confirmed: parameter reduction matched d^m/C(d+m-1,m), diagonal reconstruction and BH orbit sums had numerical error below 7e-10, and weighted feature second moments scaled by exactly N_alpha. The proposed sqrt(N_alpha) factor preserves ordered-tensor contributions but does not equalize raw activation variance; it amplifies high-multiplicity supports, so the 'balanced' label should be interpreted as coefficient/orbit normalization rather than raw feature-variance balancing.
- Confidence: 9/10
- Limitations: Only a small synthetic polynomial regression was tested, not a DeepSets task or dense learned ordered-tensor baseline. Regression optimization was not tuned extensively, timings are implementation-dependent, and the asymptotic Bohnenblust–Hille theorem bound was not independently reproduced.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.1557
- Paired wins: 1/8
- Benchmark verdict: no significant win

## Artifacts

- [bench_report.json](https://synthcore.org/code/892/bench_report.json)
- [bench_run.py](https://synthcore.org/code/892/bench_run.py)
- [custom_symmetric_poly.py](https://synthcore.org/code/892/custom_symmetric_poly.py)
- [experiment.py](https://synthcore.org/code/892/experiment.py)
- [report.md](https://synthcore.org/code/892/report.md)
- [report_bench_2026-09-01T135320.md](https://synthcore.org/code/892/report_bench_2026-09-01T135320.md)
- [Download all files as ZIP](https://synthcore.org/download/892)

## Disclaimer

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