CertMix: Certified, Data-Efficient Metamaterial Design by Affine Mixing of Aligned Neural-Implicit Weight Spaces

• URL: http://arxiv.org/abs/2607.04123v1
• Date: Sun, 05 Jul 2026 05:40:01 GMT
• Title: CertMix: Certified, Data-Efficient Metamaterial Design by Affine Mixing of Aligned Neural-Implicit Weight Spaces
• Abstract summary: Inverse design of mechanical metamaterials seeks a periodic unit cell whose homogenized elastic properties meet a prescribed target.<n>We introduce CertMix, a data-efficient framework that represents each exemplar unit cell as a small periodic neural implicit field.<n>From as few as 50 exemplars, CertMix attains a scaled property error of $10-4$, roughly two to three orders of magnitude below conditional generative baselines trained on 1000 cells.
• Score: 6.016090674751934
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Inverse design of mechanical metamaterials seeks a periodic unit cell whose homogenized elastic properties meet a prescribed target, but current learning-based methods are data-hungry, mostly interpolative, and provide no guarantee that the generated design satisfies the specification. We introduce CertMix, a data-efficient framework that represents each exemplar unit cell as a small periodic neural implicit field, specifically a SIREN signed-distance decoder overfit from a shared anchor, so that exemplar weight vectors become aligned and directly comparable. The key observation is that, in this aligned weight space, the homogenized elasticity tensor is approximately linear in the mixing coefficients. Targeted design therefore reduces to a small constrained affine-mixing problem solved with a differentiable periodic homogenizer in the loop. Negative coefficients enable extrapolation beyond the exemplar range, a linearity-mismatch trust region keeps blends valid, and split-conformal calibration converts the mismatch signal into a distribution-free certificate on achieved-property error. From as few as 50 exemplars, CertMix attains a scaled property error of $10^{-4}$, roughly two to three orders of magnitude below conditional generative baselines trained on 1000 cells. It remains accurate far outside the exemplar range, is $57\times$ faster than per-target topology optimization while avoiding checkerboards and enclosed voids, and extends to spatially graded fields, 3D triply periodic surfaces, and a certified running-shoe midsole application.

Related papers

• Exact Degeneracy Under Balanced k-Shot Sampling:Consequences for Small-Sample Discriminant Analysis on LLM Embeddings [0.0]
  We show that balanced k-shot sampling induces an exact, provable degeneracy in a family of small-sample discriminant estimators.<n>We then evaluate the Kernelgression repaired framework on few-shot text classification on frozen embeddings.
  arXiv  Detail & Related papers  (2026-09-09T08:13:54Z)
• Scalable Lindblad Noise Learning via Stochastic Tensor-Network Simulation [48.887627688666974]
  Learning dissipation rates in large-scale open quantum systems is a major obstacle for near-term quantum technologies.<n>Here, we propose a scalable noise-learning framework for Lindblad dissipation rates that combines a simulation method, the Jump Method (TJM)<n>We demonstrate the approach on two noise models in the Ising model, in which independent dissipation rates are learned for each site up to $N_mathrmsite=16$.<n>This combination of scalable numerics and rigorous theoretical guarantees positions TJM-based noise learning as a practical foundation for characterizing dissipation in large quantum devices.
  arXiv  Detail & Related papers  (2026-08-25T15:07:11Z)
• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• Exact computation of posterior distribution of mixture weights in hierarchical Bayesian models [0.0]
  This paper studies the exact marginalization of the mixture weight.<n>We show that the exact posterior of the weight is a finite mixture of Beta distributions.<n>The gain is largest in the small-sample regime the method is built for.
  arXiv  Detail & Related papers  (2026-07-06T23:20:43Z)
• An Adaptive Data cleaning Framework for Noisy Label Detection [0.0]
  Deep neural networks (DNNs) excel in computer vision tasks given large annotated datasets.<n>In real-world applications, labels are often corrupted by ambiguity, human error, or dynamic environments.<n>This paper proposes a self-adaptive data-cleaning framework that integrates local, global, and learning dynamics cues for robust noisy-label detection.
  arXiv  Detail & Related papers  (2026-06-05T09:32:18Z)
• Non-Vacuous Certification of Transport MCMC via Oscillation-Controlled Normalizing Flows [3.8549131582427303]
  Transport MCMC trains a normalizing flow to precondition Metropolis--Hastings proposals.<n>We establish the first numerically non-vacuous, rigorous spectral-gap bound for such samplers.
  arXiv  Detail & Related papers  (2026-05-31T07:46:48Z)
• From Latent Space to Training Data: Explainable Specialization in Minimal MLPs [0.47554242259005197]
  We study whether training biases can make hidden neurons specialize in minimal one-hidden-layers.<n>Experiments on uniformly sampled one-dimensional datasets show a stable pattern from N = 3 to N = 100 across 480 controlled runs.
  arXiv  Detail & Related papers  (2026-05-25T15:18:22Z)
• Phase-space entropy at acquisition reflects downstream learnability [54.4100065023873]
  We propose an acquisition-level scalar $S_mathcal B$ based on instrument-resolved phase space.<n>We show theoretically that (S_mathcal B) correctly identifies the phase-space coherence of periodic sampling.<n>$|S_mathcal B|$ consistently ranks sampling geometries and predicts downstream reconstruction/recognition difficulty emphwithout training.
  arXiv  Detail & Related papers  (2025-12-22T10:03:51Z)
• Benign Overfitting and the Geometry of the Ridge Regression Solution in Binary Classification [75.01389991485098]
  We show that ridge regression has qualitatively different behavior depending on the scale of the cluster mean vector.<n>In regimes where the scale is very large, the conditions that allow for benign overfitting turn out to be the same as those for the regression task.
  arXiv  Detail & Related papers  (2025-03-11T01:45:42Z)
• Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion [55.95767828747407]
  In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model.<n>We present a framework that reduces training variance and provides a provably lower-variance gradient estimator.<n>We also present a practical implementation of this estimator incorporating the loss and sampling procedure through a method we call Orbit Diffusion.
  arXiv  Detail & Related papers  (2025-02-14T03:26:57Z)
• SIGMA: Scale-Invariant Global Sparse Shape Matching [50.385414715675076]
  We propose a novel mixed-integer programming (MIP) formulation for generating precise sparse correspondences for non-rigid shapes. We show state-of-the-art results for sparse non-rigid matching on several challenging 3D datasets.
  arXiv  Detail & Related papers  (2023-08-16T14:25:30Z)
• Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning [99.14132861655223]
  We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining. Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
  arXiv  Detail & Related papers  (2022-11-29T14:52:38Z)
• Adversarial Mixing Policy for Relaxing Locally Linear Constraints in Mixup [7.272501519394588]
  Mixup is a recent regularizer for current deep classification networks. We propose the Adversarial Mixing Policy (AMP) to relax the Locally Linear Constraints in Mixup. AMP adds a small adversarial perturbation to the mixing coefficients rather than the examples.
  arXiv  Detail & Related papers  (2021-09-15T09:31:59Z)
• MIX'EM: Unsupervised Image Classification using a Mixture of Embeddings [44.29313588655997]
  We present MIX'EM, a novel solution for unsupervised image classification. We conduct extensive experiments and analyses on STL10, CIFAR10, and CIFAR100-20 datasets. We achieve state-of-the-art classification accuracy of 78%, 82%, and 44%, respectively.
  arXiv  Detail & Related papers  (2020-07-18T19:24:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.