# Critical stochastic min-plus tree layer

- ID: 2176
- Canonical URL: https://synthcore.org/idea/2176/critical-stochastic-min-plus-tree-layer
- API JSON: https://synthcore.org/api/idea/2176.json
- API Markdown: https://synthcore.org/api/idea/2176.md
- Verification status: failed_benchmark
- Source: [arXiv:2608.12295](https://arxiv.org/abs/2608.12295)
- Category: architecture
- Solves: stability, generalization, sample-efficiency
- ML areas: mlp, cnn, training-dynamics, regularization
- Math tags: statistical-mechanics, dynamical-systems, probability, bifurcations
- Ratings: usefulness 7/10; difficulty 5/10; novelty 8/10

## Idea description

Replace deterministic binary-tree pooling or hierarchical feature aggregation by a stochastic merge that chooses either elementwise addition or elementwise minimum. The mixing probability p controls whether zero or sparse states proliferate or disappear, with a predicted absorbing-state transition at p = 1/2.

## Mathematical statement

For nonnegative scalar or coordinatewise feature values x and y, define a random merge M_p(x,y) equal to x + y with probability p and min(x,y) with probability 1 - p. If leaf activations are Bernoulli, with probability q of being exactly zero, and z_n = P(X_n = 0) is the zero probability at tree level n, independence of sibling subtrees gives z_(n+1) = p z_n^2 + (1-p)(2 z_n - z_n^2) = 2(1-p)z_n + (2p-1)z_n^2. The fixed points are z = 0 and z = 1. The critical point is p_c = 1/2; at criticality z_n = q for every depth n. For p > 1/2, zero mass decreases toward zero, whereas for p < 1/2, it increases toward one.

## Key formulas

- $M_p(x,y) = x+y$ with probability p, and $M_p(x,y) = min(x,y)$ with probability 1-p
- $z_{n+1} = p z_n^2 + (1-p)(2z_n-z_n^2) = 2(1-p)z_n + (2p-1)z_n^2$
- $z_{n+1}-z_n = (1-2p)z_n(1-z_n), \quad p_c = 1/2$
- $p=1/2 \implies z_n=z_0=q \text{ for every } n$

## Implementation notes

Integration point: implement a binary-tree or hierarchical feature block in an MLP, CNN pyramid, or graph pooling module. For two feature vectors u and v in the nonnegative orthant, sample a Bernoulli gate B with parameter p and compute w = B times (u + v) plus (1-B) times min(u,v), coordinatewise. Follow each merge with normalization and a learned projection if the feature dimension changes. Pseudocode: initialize nonnegative leaf features; at every tree level pair siblings; sample B for each pair or channel; calculate the stochastic merge; record the fraction of exact zeros; continue to the root; optimize the task loss with straight-through sampling or ordinary autodiff through the selected branch. Compute from the paper the recursion and critical value p_c = 1/2. Estimate empirically the effect of finite width, sibling correlations, normalization, and gradient routing. First experiment: train a four- to eight-level tree MLP on MNIST or CIFAR-10, comparing sum pooling, min pooling, and fixed p values 0.25, 0.4, 0.5, 0.6, and 0.75. Measure zero fraction z_n at every level, gradient norm by depth, and accuracy. The quantitative prediction is that at p = 0.5, z_n remains approximately equal to the leaf zero rate q; for p above 0.5 it decreases, and for p below 0.5 it increases. Fit the observed recursion and require the estimated transition to be within 0.05 of p = 0.5.

## Verification

- Status: failed_benchmark
- Mechanism evidence: yes
- Mechanism confirmed: no
- Practical verdict: inconclusive
- Verdict: Built a NumPy implementation of the stochastic min-plus binary-tree merge and verified the claimed mechanism. Monte Carlo matched the exact zero-mass recursion with maximum absolute error 0.00186; the fitted transition was p=0.500000, and depth/q sweeps confirmed critical invariance at p=0.5 plus convergence toward one below and zero above criticality. The toy classifier comparison did not show a general task win: sum/min/critical-stochastic accuracies were 0.498/0.604/0.542, so the positive result is specifically the predicted absorbing-state mechanism, not downstream accuracy.

### Mechanism check

- Verdict: Built a NumPy implementation of the stochastic min-plus binary-tree merge and verified the claimed mechanism. Monte Carlo matched the exact zero-mass recursion with maximum absolute error 0.00186; the fitted transition was p=0.500000, and depth/q sweeps confirmed critical invariance at p=0.5 plus convergence toward one below and zero above criticality. The toy classifier comparison did not show a general task win: sum/min/critical-stochastic accuracies were 0.498/0.604/0.542, so the positive result is specifically the predicted absorbing-state mechanism, not downstream accuracy.
- Confidence: 9/10
- Limitations: The downstream comparison is a small NumPy toy classifier rather than a full MNIST/CIFAR MLP or CNN. It does not measure gradient routing, learned projections, normalization effects, FLOPs, or finite-width feature correlations; the exact recursion check uses independent Bernoulli zero states, where its assumptions hold by construction.

### Practical benchmark

- Paired seeds: 8
- Baseline mean: 0
- Idea mean: 0
- p-value: 0.20525
- Paired wins: 5/8
- Benchmark verdict: no significant win

## Artifacts

- [bench_experiment.py](https://synthcore.org/code/870/bench_experiment.py)
- [bench_report.json](https://synthcore.org/code/870/bench_report.json)
- [experiment.py](https://synthcore.org/code/870/experiment.py)
- [report.md](https://synthcore.org/code/870/report.md)
- [report_bench_2026-09-01T131624.md](https://synthcore.org/code/870/report_bench_2026-09-01T131624.md)
- [results.json](https://synthcore.org/code/870/results.json)
- [Download all files as ZIP](https://synthcore.org/download/870)

## Disclaimer

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