{
 "artifacts": null,
 "category": "regularization",
 "description": "Add a fractional-Laplacian penalty to a neural network evaluated on binary inputs or binary latent gates. For 1 \u003c p \u003c 2, the endpoint inequality implies that controlling fractional spectral energy controls the L_p norm of aggregate coordinate-flip sensitivity, potentially giving a more global robustness objective than explicitly enumerating one-bit perturbations.",
 "formulas_latex": [
  "$$D_j f(x)=\\frac{f(x)-f(x^{(j)})}{2},\\qquad \\Delta f=\\sum_{j=1}^{n}D_j f$$",
  "$$\\left\\|\\left(\\sum_{j=1}^{n}|D_jf|^{2}\\right)^{1/2}\\right\\|_{p}\\lesssim_{p}\\|\\Delta^{1/p}f\\|_{p},\\qquad 1\u003cp\u003c2$$",
  "$$f(x)=\\sum_{S\\subseteq[n]}\\widehat f(S)\\chi_S(x),\\quad \\chi_S(x)=\\prod_{j\\in S}x_j,\\quad \\Delta^{1/p}f(x)=\\sum_{S\\ne\\varnothing}|S|^{1/p}\\widehat f(S)\\chi_S(x)$$",
  "$$\\mathcal L(\\theta)=\\mathcal L_{\\mathrm{task}}(\\theta)+\\lambda\\,\\mathbb E_{x\\sim\\mathrm{Unif}(\\Omega_n)}\\left[\\left|\\Delta^{1/p}f_\\theta(x)\\right|^p\\right]$$"
 ],
 "id": 3158,
 "implementation": "Integrate the method at the model-output interface for a classifier or encoder whose input is x in {-1,1}^n, including binary feature vectors, token-presence indicators, or hard binary routing gates. Do not apply it directly to continuous hidden activations unless those activations are first discretized. For a first implementation with n \u003c= 14, enumerate all cube points or use a fixed random subset, evaluate the scalar output f_theta(x), apply a fast Walsh-Hadamard transform to obtain the coefficients f_hat(S), multiply coefficient S by |S|^(1/p) for every nonempty S and set the constant coefficient to zero, then apply the inverse transform. Use the following loop: `y = model(theta, x_cube)`; `coeff = FWHT(y)`; `coeff[0] = 0`; for each spectral index S, set `coeff[S] = coeff[S] * popcount(S)**(1/p)`; `z = IFWHT(coeff)`; `loss = task_loss + lambda * mean(abs(z)**p)`; backpropagate and update theta. For larger n, retain only low-order Walsh subsets or estimate coefficients by Monte Carlo sampling of chi_S(x); validate the approximation against exact transforms on small n. The paper supplies the sensitivity-to-fractional-energy inequality, while the Walsh diagonalization and truncation are implementation choices. Begin with a two-layer MLP on a synthetic parity-plus-noise task or binarized MNIST using n = 12 or 16 input bits. Compare ordinary cross-entropy, explicit one-bit-flip augmentation, and this penalty at matched FLOPs. Measure clean accuracy, accuracy under one-, two-, and four-bit flips, empirical sensitivity E[(sum_j |D_j f|^2)^(p/2)], and training loss at equal step count. Success means lower flip sensitivity and improved corrupted accuracy at comparable clean accuracy, or matching robustness with fewer explicit perturbation evaluations.",
 "math_summary": "The paper defines the Hamming cube Omega_n = {-1,1}^n with normalized counting measure, the coordinate flip x^(j), the discrete derivative D_j f(x) = (f(x) - f(x^(j)))/2, the gradient nabla f = (D_1 f,...,D_n f), and the Laplacian Delta f = sum_j D_j f. Its endpoint theorem states that for every 1 \u003c p \u003c 2, ||(sum_j |D_j f|^2)^(1/2)||_p \u003c= C_p ||Delta^(1/p) f||_p, where C_p depends only on p and not on dimension n. For implementation, expand a scalar network output f_theta on the Walsh basis chi_S(x) = product_{j in S} x_j, for S a subset of {1,...,n}. Because Delta chi_S = |S| chi_S, the fractional operator is Delta^(1/p) f = sum_{S != emptyset} |S|^(1/p) f_hat(S) chi_S, with the constant mode removed because its Laplacian eigenvalue is zero. Use the computable regularizer R_frac = E_x[|Delta^(1/p) f_theta(x)|^p]. The theorem supplies the dimension-free sensitivity-control relation; the exact constant C_p is not required during optimization.",
 "math_tags": [
  "harmonic-analysis",
  "spectral-theory",
  "functional-analysis"
 ],
 "ml_areas": [
  "loss",
  "regularization",
  "embedding"
 ],
 "paper": {
  "arxiv_id": "2609.03993",
  "arxiv_url": "https://arxiv.org/abs/2609.03993",
  "summary_what_math_gives_to_ml": "The paper proves a dimension-free endpoint estimate on the Boolean cube: for 1 \u003c p \u003c 2, aggregate coordinate sensitivity is controlled by a fractional Laplacian of order 1/p, even though the usual square-root Riesz estimate fails in this range. The transferable asset is a principled way to penalize sensitivity to many binary feature flips using fractional spectral energy rather than enumerating every perturbation. A practical neural-network adaptation is a robustness regularizer for binary inputs, discrete features, or learned binary gates, with the fractional Laplacian computed through a Walsh transform on small cubes or a truncated spectral estimator at larger dimension.",
  "title": "The Endpoint Fractional Riesz Estimate on the Hamming Cube",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 5,
  "novelty": 7,
  "usefulness": 5
 },
 "solves": [
  "stability",
  "generalization",
  "accuracy"
 ],
 "title": "Fractional Boolean Sensitivity Regularization",
 "url": "https://synthcore.org/idea/3158/fractional-boolean-sensitivity-regularization",
 "verification": {
  "peer_reviewed": false,
  "status": "unverified",
  "status_label": "Unverified",
  "verdict_source": "deterministic test code (paired-seed permutation statistics)",
  "verification_axes": {
   "benchmark_mechanism": {
    "confirmed": null,
    "tested": false
   },
   "practical_benchmark": {
    "beats_baseline": null,
    "tested": false
   },
   "toy_mechanism_gate": {
    "confirmed": null,
    "tested": false
   }
  }
 }
}