Deterministic Mapping of Topological Phases via Autoregressive Exogenous Neural Networks

• URL: http://arxiv.org/abs/2605.27300v1
• Date: Tue, 26 May 2026 17:11:22 GMT
• Title: Deterministic Mapping of Topological Phases via Autoregressive Exogenous Neural Networks
• Abstract summary: Three dynamic neural network (NN) architectures -- NAR, NARX, and NIO -- are evaluated.<n>We show that NARX achieves superior predictive fidelity, reaching a Mean Squared Error (MSE) of $10-27$.<n>We observe a "complexity paradox" where the NARX model's accuracy collapses at higher delays.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We report a comparative analysis of three dynamic neural network (NN) architectures -- NAR, NARX, and NIO -- to evaluate their efficiency in estimating the critical-measurement-strength parameter ($c_{crit}$) characterizing topological phase transitions in geometric phases induced by weak measurements. Our results demonstrate that the NARX architecture achieves superior predictive fidelity, reaching a Mean Squared Error (MSE) of $10^{-27}$ -- the limit of numerical precision -- at an optimal delay of $d=1$. This exceptional performance implies the identification of a perfect functional identity, suggesting that the relationship between winding numbers $W$ and $c_{crit}$ is mathematically deterministic. We observe a "complexity paradox" where the NARX model's accuracy collapses at higher delays ($d=4$), a phase-sensitivity that confirms the model captures a high-precision dynamic mapping rather than a trivial pattern. While the NAR model remains robust for local-trend capture, the NIO architecture fails to accurately resolve the phase transition despite increased neuronal capacity. These findings underscore that both autoregressive feedback and immediate exogenous context are essential for the exact characterization of topological phases, establishing NARX as a robust framework for deriving governing laws in complex quantum systems, where analytical solutions remain elusive.

Related papers

• Eigenanalysis framework for autoregressive neural emulators of multi-scale chaotic dynamics [37.134314242843914]
  We develop an eigenanalysis framework that reveals the dynamical origin of error growth.<n>We show how inference-time error growth is governed by its spectral radius.<n>Our results establish a theoretical foundation for the design and evaluation of neural emulators of chaotic multi-scale dynamics.
  arXiv  Detail & Related papers  (2026-08-17T04:30:03Z)
• Multimodal Molecular Representation Learning with Graph Neural Networks, Deep & Cross Networks, and SMILES Embeddings [2.9593641578445258]
  We introduce a parameter-efficient Tri-Branch Modular Fusion Network that synthesizes three modalities: 3D spatial geometry (SchNet), discrete topological grammar (SMILES via ChemBERTa), and explicit macroscopic physicochemical descriptors (Deep & Cross Network)<n> operating with fewer than one million parameters, this architecture decisively surpasses the sub-chemical accuracy threshold and yields a substantial 20.6% reduction over a strictly controlled geometric baseline.
  arXiv  Detail & Related papers  (2026-07-07T01:47:44Z)
• LRX-PINN: A Layer-Resolving XNet Physics-Informed Neural Network with Integrated Cauchy Activations for Convection-Dominated Problems [7.72118589117645]
  Layer-Resolving XNet Physics-Informed Neural Network (LRX-PINN) based on integrated Cauchy activations.<n>We show that this structure matches the scaling of convection-dominated layers, inherits the Cauchy approximation mechanism at the derivative-profile level, and identifies (d/|w|) as the effective physical width of a ridge neuron.<n> Numerical experiments on several convection-dominated benchmarks show that LRX-PINN achieves higher accuracy than PIKAN and Fourier-feature PINNs while using less than (30%) of their trainable parameters.
  arXiv  Detail & Related papers  (2026-07-04T03:25:05Z)
• When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms [43.8784307709823]
  Long-horizon autoregressive forecasting of physical signals is limited by error accumulation.<n>We ask when such rollout stays stable using synthetic three-component seismograms as a physically structured testbed.
  arXiv  Detail & Related papers  (2026-06-09T13:46:14Z)
• Hybrid LSTM-Graph Neural Framework for Robust Financial Fraud Detection and Adversarial Resilience [0.0]
  This paper proposes FraudShield AI, a hybrid framework that integrates Long Short-Term Memory (LSTM) networks with hand-crafted Graph Topological Features.<n>A Focal Loss objective is used to address class imbalance, and a dynamic thresholding mechanism is introduced to improve resilience against low-value smurfing attacks.
  arXiv  Detail & Related papers  (2026-05-02T02:10:20Z)
• From Arithmetic to Logic: The Resilience of Logic and Lookup-Based Neural Networks Under Parameter Bit-Flips [0.6868507883617846]
  In this work, we study resilience as a structural property of neural architectures.<n>We show that lower precision, higher sparsity, bounded activations, and shallow depth are consistently favored.<n>We identify a novel even-layer recovery effect unique to logic-based architectures.
  arXiv  Detail & Related papers  (2026-03-24T03:53:04Z)
• DNA: Uncovering Universal Latent Forgery Knowledge [39.19379714306656]
  forgery detection capability is already encoded within pre-trained models.<n>DNA framework employs a coarse-to-fine excavation mechanism.<n>Hifi-Gen is a high-fidelity synthetic benchmark built upon the very latest models.
  arXiv  Detail & Related papers  (2026-01-30T03:48:30Z)
• On the Identifiability of Regime-Switching Models with Multi-Lag Dependencies [42.274922469778545]
  We develop a general theoretical framework for multi-lag Regime-Switching Models (RSMs)<n>We prove identifiability of both the number of regimes and the multi-lag transitions in a nonlinear-Gaussian setting.<n>Our results hold in a fully unsupervised setting through architectural and noise assumptions.
  arXiv  Detail & Related papers  (2026-01-06T15:12:39Z)
• Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware [78.17783007774295]
  This paper explores the potential of conversion-based neuromorphic algorithms for highly accurate and energy-efficient single-snapshot multidimensional harmonic retrieval.<n>A novel method for converting the complex-valued convolutional layers and activations into spiking neural networks (SNNs) is developed.<n>The converted SNNs achieve almost five-fold power efficiency at moderate performance loss compared to the original CNNs.
  arXiv  Detail & Related papers  (2024-12-05T09:41:33Z)
• A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization [90.87444114491116]
  This paper studies minimax optimization problems defined over infinite-dimensional function classes of overparametricized two-layer neural networks. We address (i) the convergence of the gradient descent-ascent algorithm and (ii) the representation learning of the neural networks. Results show that the feature representation induced by the neural networks is allowed to deviate from the initial one by the magnitude of $O(alpha-1)$, measured in terms of the Wasserstein distance.
  arXiv  Detail & Related papers  (2024-04-18T16:46:08Z)
• Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis [16.893624100273108]
  We analyze recurrent neural networks with diagonal hidden-to-hidden weight matrices trained with gradient descent in the supervised learning setting. We prove that gradient descent can achieve optimality emphwithout massive over parameterization. Our results are based on an explicit characterization of the class of dynamical systems that can be approximated and learned by recurrent neural networks.
  arXiv  Detail & Related papers  (2024-02-19T15:56:43Z)
• Consistency Models for Scalable and Fast Simulation-Based Inference [9.27488642055461]
  We present consistency models for posterior estimation (CMPE), a new conditional sampler for simulation-based inference ( SBI) CMPE essentially distills a continuous probability flow and enables rapid few-shot inference with an unconstrained architecture. Our empirical evaluation demonstrates that CMPE not only outperforms current state-of-the-art algorithms on hard low-dimensional benchmarks, but also achieves competitive performance with much faster sampling speed.
  arXiv  Detail & Related papers  (2023-12-09T02:14:12Z)
• Edge of stability echo state networks [5.888495030452654]
  Echo State Networks (ESNs) are time-series processing models working under the Echo State Property (ESP) principle. We introduce a new ESN architecture, called the Edge of Stability Echo State Network (ES$2$N)
  arXiv  Detail & Related papers  (2023-08-05T15:49:25Z)

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.