Generative Inverse Design with Abstention via Diagonal Flow Matching

• URL: http://arxiv.org/abs/2603.15925v1
• Date: Mon, 16 Mar 2026 21:18:16 GMT
• Title: Generative Inverse Design with Abstention via Diagonal Flow Matching
• Abstract summary: Inverse design aims to find design parameters $x$ achieving target performance $y*$.<n>Standard conditional flow matching (CFM) exhibits strong sensitivity to their arbitrary ordering and scaling, leading to unstable training.<n>We introduce Diagonal Flow Matching (Diag-CFM), which resolves this through a zero-anchoring strategy that pairs design coordinates with noise and labels with zero.<n>This yields order-of-magnitude improvements in round-trip accuracy over CFM and invertible neural network baselines across design dimensions up to $P=100$.
• Score: 2.888595212660871
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Inverse design aims to find design parameters $x$ achieving target performance $y^*$. Generative approaches learn bidirectional mappings between designs and labels, enabling diverse solution sampling. However, standard conditional flow matching (CFM), when adapted to inverse problems by pairing labels with design parameters, exhibits strong sensitivity to their arbitrary ordering and scaling, leading to unstable training. We introduce Diagonal Flow Matching (Diag-CFM), which resolves this through a zero-anchoring strategy that pairs design coordinates with noise and labels with zero, making the learning problem provably invariant to coordinate permutations. This yields order-of-magnitude improvements in round-trip accuracy over CFM and invertible neural network baselines across design dimensions up to $P{=}100$. We develop two architecture-intrinsic uncertainty metrics, Zero-Deviation and Self-Consistency, that enable three practical capabilities: selecting the best candidate among multiple generations, abstaining from unreliable predictions, and detecting out-of-distribution targets; consistently outperforming ensemble and general-purpose alternatives across all tasks. We validate on airfoil, gas turbine combustor, and an analytical benchmark with scalable design dimension.

Related papers

• Adaptively Incorporating Directional Hints into Zeroth-Order Optimization [49.940317286021696]
  We develop an algorithm that achieves zeroth-order optimization of non- functions with the aid directional hints.<n>We validate the method, demonstrating sustained progress on non- control tasks.
  arXiv  Detail & Related papers  (2026-09-08T05:42:02Z)
• Formulation-Level Auto-Tuning for QUBO-Based Machine Learning: A Case Study Across Multiple Quantum-Inspired Annealers [0.0]
  This paper presents an Optuna-based formulation-level auto-tuning framework for support vector machines (SVMs)<n> continuous dual variables are discretized and converted into a quadratic unconstrained binary optimization (QUBO) model.<n>Experiments on linear and nonlinear classification tasks with 0-20% label noise show mean gains over grid search of approximately 0.8 and 2.1 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-07-21T06:56:43Z)
• GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators [9.058225799011545]
  GIST (Gauge-Invariant Spectral Transformers) is a new graph transformer architecture that achieves end-to-end $mathcalO(N)$ complexity through random projections.<n>We prove GIST achieves discretization-invariant learning with bounded mismatch error, enabling parameter transfer across arbitrary mesh resolutions for neural operator applications.
  arXiv  Detail & Related papers  (2026-03-17T17:54:26Z)
• How well do generative models solve inverse problems? A benchmark study [2.374976152884002]
  Generative learning generates high dimensional data based on low dimensional conditions, also called prompts.<n>We compare a traditional Bayesian inverse approach with three state of the art generative learning models, namely conditional Generative Adversarial Networks, Invertible Neural Networks and Conditional Flow Matching.<n>Our benchmark has a clear winner, as Conditional Flow Matching consistently outperforms all competing approaches.
  arXiv  Detail & Related papers  (2026-01-30T18:06:50Z)
• Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoders [24.716251378991288]
  Counterfactual explanations (CEs) provide recourse recommendations for individuals affected by algorithmic decisions.<n>Existing methods mostly struggle to address these multifaceted requirements in a unified, model-agnostic manner.<n>We present LAPACE, a model-agnostic algorithm that synthesises entire paths of CE points by interpolating from inputs' latent representations to those learned latent centroids.
  arXiv  Detail & Related papers  (2025-10-06T14:42:23Z)
• Self-Supervised Any-Point Tracking by Contrastive Random Walks [17.50529887238381]
  We train a global matching transformer to find cycle consistent tracks through video via contrastive random walks. Our method achieves strong performance on the TapVid benchmarks, outperforming previous self-supervised tracking methods.
  arXiv  Detail & Related papers  (2024-09-24T17:59:56Z)
• Compositional Generative Inverse Design [69.22782875567547]
  Inverse design, where we seek to design input variables in order to optimize an underlying objective function, is an important problem. We show that by instead optimizing over the learned energy function captured by the diffusion model, we can avoid such adversarial examples. In an N-body interaction task and a challenging 2D multi-airfoil design task, we demonstrate that by composing the learned diffusion model at test time, our method allows us to design initial states and boundary shapes.
  arXiv  Detail & Related papers  (2024-01-24T01:33:39Z)
• Transformers as Support Vector Machines [54.642793677472724]
  We establish a formal equivalence between the optimization geometry of self-attention and a hard-margin SVM problem. We characterize the implicit bias of 1-layer transformers optimized with gradient descent. We believe these findings inspire the interpretation of transformers as a hierarchy of SVMs that separates and selects optimal tokens.
  arXiv  Detail & Related papers  (2023-08-31T17:57:50Z)
• 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)
• Uncertainty Guided Adaptive Warping for Robust and Efficient Stereo Matching [77.133400999703]
  Correlation based stereo matching has achieved outstanding performance. Current methods with a fixed model do not work uniformly well across various datasets. This paper proposes a new perspective to dynamically calculate correlation for robust stereo matching.
  arXiv  Detail & Related papers  (2023-07-26T09:47:37Z)
• Task-Oriented Over-the-Air Computation for Multi-Device Edge AI [57.50247872182593]
  6G networks for supporting edge AI features task-oriented techniques that focus on effective and efficient execution of AI task. Task-oriented over-the-air computation (AirComp) scheme is proposed in this paper for multi-device split-inference system.
  arXiv  Detail & Related papers  (2022-11-02T16:35:14Z)
• Transformers meet Stochastic Block Models: Attention with Data-Adaptive Sparsity and Cost [53.746169882193456]
  Recent works have proposed various sparse attention modules to overcome the quadratic cost of self-attention. We propose a model that resolves both problems by endowing each attention head with a mixed-membership Block Model. Our model outperforms previous efficient variants as well as the original Transformer with full attention.
  arXiv  Detail & Related papers  (2022-10-27T15:30:52Z)
• Mixed Integer Neural Inverse Design [27.43272793942742]
  piecewise linear property, very common in everyday neural networks, allows for an inverse design formulation based on mixed-integer linear programming. Our mixed-integer inverse design uncovers globally optimal or near optimal solutions in a principled manner.
  arXiv  Detail & Related papers  (2021-09-27T09:19:41Z)

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.