{
 "artifacts": null,
 "category": "regularization",
 "description": "Apply a regularizer that penalizes feature disagreement under a finite set of known transformations. The paper's spectral-gap inequality gives a quantitative reason that this local consistency penalty controls distance from the subspace invariant under the transformation group, while the task loss prevents undesirable collapse.",
 "formulas_latex": [
  "$$\\max_{q\\in Q}\\|\\rho(q)x-x\\|_p\\geq c_p\\,\\operatorname{dist}\\bigl(x,X^{\\rho(G)}\\bigr).$$",
  "$$X^{\\rho(G)}=\\{x\\in X:\\rho(g)x=x\\ \\text{for every }g\\in G\\},\\qquad \\operatorname{dist}(x,X^{\\rho(G)})=\\inf_{y\\in X^{\\rho(G)}}\\|x-y\\|_p.$$",
  "$$\\Phi(x)(\\omega)=\\operatorname{sgn}(x(\\omega))|x(\\omega)|^m,\\qquad p=2m,\\qquad \\|\\Phi(x)\\|_2^2=\\|x\\|_{2m}^{2m}.$$",
  "$$\\mathcal L_{\\mathrm{gap}}(z)=\\frac{1}{|Q|}\\sum_{q\\in Q}\\|\\rho(q)z-z\\|_p^p,\\qquad \\mathcal L_{\\mathrm{inv}}(z)=\\left\\|z-\\frac{1}{|Q|}\\sum_{q\\in Q}\\rho(q)z\\right\\|_p^p.$$"
 ],
 "id": 3008,
 "implementation": "1. Integration point: insert the regularizer after an intermediate feature tensor z = f_theta(x), before the classifier or decoder head. Choose Q as a small set of transformations such as rotations, reflections, graph automorphisms, token permutations, or domain-specific symmetries. Implement rho(q) as a permutation or signed permutation of feature coordinates whenever possible. If the transformation acts on inputs instead, compute z_q = f_theta(qx) and use z_q as the transformed representation.\n\n2. Pseudocode: `z = encoder(x)`; `zq = [rho(q, z) for q in Q]`; `gap = mean([mean(abs(v - z)**p) for v in zq])`; `zmean = mean(zq)`; `inv = mean(abs(z - zmean)**p)`; `loss = task_loss(head(z), y) + lambda_gap * gap + lambda_inv * inv`. For p = 2m, optionally compute `phi(v) = sign(v) * abs(v)**m` and add `gap2 = mean([mean((phi(v) - phi(z))**2) for v in zq])`, normalized by `mean(phi(z)**2) + epsilon`.\n\n3. The mathematical result supplies the spectral-gap principle and the dependence on p and the representation's Kazhdan constant, but c_p will normally be unknown in an ML application. Estimate an empirical diagnostic with `ratio = max_q norm_p(rho(q,z) - z) / (norm_p(z - mean_q rho(q,z)) + epsilon)`. The finite average is only an approximate projector unless Q covers the full group, so keep the supervised task loss and monitor covariance rank to detect feature collapse. Tune lambda_gap so that the regularizer is initially between 1 and 10 percent of the task loss.\n\n4. First cheap experiment: use a ResNet-18 on CIFAR-10. Let Q be the four rotations, or the dihedral set of rotations and horizontal reflections, and compare a baseline, ordinary pairwise consistency loss, and the L4 spectral-gap regularizer at matched training FLOPs. Measure clean accuracy, accuracy on rotated and corrupted test images, transformation disagreement, feature covariance effective rank, and the empirical ratio. The method is supported if it improves transformed or corrupted accuracy and reduces disagreement without materially reducing clean accuracy or feature rank.",
 "math_summary": "The main estimate states that for a sigma-finite measure space (Omega, Sigma, mu), a closed subspace X of L_p(mu), a strongly continuous isometric representation rho from G to O(X), a finite set Q in G, and x in X, there exists c_p greater than zero such that max over q in Q of ||rho(q)x - x||_p is at least c_p times dist(x, X^{rho(G)}). Here O(X) is the group of linear L_p-isometries, X^{rho(G)} = {x in X : rho(g)x = x for every g in G} is the invariant subspace, and dist(x, X^{rho(G)}) = inf over y in X^{rho(G)} of ||x-y||_p. For even p = 2m, the paper uses the power map Phi(x)(omega) = sgn(x(omega)) |x(omega)|^m, which satisfies ||Phi(x)||_2^2 = ||x||_{2m}^{2m}, thereby converting L_{2m} magnitudes into Hilbert-space magnitudes. In a neural network, use a finite-group average as an approximate invariant projector and penalize the residual in L_p.",
 "math_tags": [
  "representation-theory",
  "functional-analysis",
  "geometry",
  "spectral-theory"
 ],
 "ml_areas": [
  "regularization",
  "cnn"
 ],
 "paper": {
  "arxiv_id": "2609.01447",
  "arxiv_url": "https://arxiv.org/abs/2609.01447",
  "summary_what_math_gives_to_ml": "The paper proves a uniform spectral-gap inequality for isometric representations on closed subspaces of L_p, extending Hilbert-space property-T behavior to non-Hilbert feature geometries. The transferable asset is the quantitative principle that disagreement under a finite transformation set controls distance from the invariant feature subspace. This can become a group-augmentation regularizer for neural representations, with the power map x to x^m at even p providing a Hilbert-space proxy for implementation.",
  "title": "Kazhdan's Property $(T)$ for Subspaces and Quotients of $L_p$-Spaces",
  "year": "2026"
 },
 "ratings": {
  "difficulty": 5,
  "novelty": 5,
  "usefulness": 5
 },
 "solves": [
  "generalization",
  "stability",
  "accuracy"
 ],
 "title": "Lp Spectral-Gap Invariance Regularizer",
 "url": "https://synthcore.org/idea/3008/lp-spectral-gap-invariance-regularizer",
 "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
   }
  }
 }
}