An Embedded RISC-V Evaluation of Kolmogorov--Arnold Networks in Hard-Constrained Recurrent Physics-Informed Models

• URL: http://arxiv.org/abs/2608.00737v1
• Date: Sat, 01 Aug 2026 16:20:24 GMT
• Title: An Embedded RISC-V Evaluation of Kolmogorov--Arnold Networks in Hard-Constrained Recurrent Physics-Informed Models
• Abstract summary: Kolmogorov--Arnold Networks (KANs) have been proposed as efficient replacements for multilayer perceptrons (MLPs)<n>This paper asks whether that parameter efficiency survives deployment.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Hard-constrained recurrent physics-informed networks (HRPINNs) embed known dynamics inside a recurrent numerical integrator and restrict a neural branch to learning only the residual dynamics that the first-principles model does not capture. Kolmogorov--Arnold Networks (KANs) have been proposed as parameter-efficient replacements for multilayer perceptrons (MLPs) in such residual branches, but their learnable B-spline activations follow a markedly different execution profile. Building on prior work that characterized when a vanilla B-spline KAN matches or underperforms an MLP as an HRPINN residual branch in discovery accuracy, this paper asks whether that parameter efficiency survives deployment. Using identical trained weights, we measured execution latency, energy per integration step, and dependability under post-training quantization in the closed recurrent loop on a RISC-V RV64GC platform without vector extensions (StarFive VisionFive~2, SiFive U74). For the two accuracy-comparable pairs, the KAN residual branch executed $13.5\times$ and $8.0\times$ slower and consumed $11.3\times$ and $5.6\times$ more energy per integration step (3.7\,$μ$J against 0.33\,$μ$J for the smallest pair); across all four parameter-matched size tiers the ranges are $4.7\times$--$14.5\times$ and $4.7\times$--$18.7\times$. Under INT8 quantization, KAN trajectories diverged up to $43\times$ earlier than matched MLPs; the damage traces to weight quantization, not to input-side knot-interval misassignment. These results indicate that the parameter efficiency reported for KANs does not transfer to deployment cost on scalar embedded cores, and that an MLP residual branch is the more dependable default for embedded HRPINN deployment unless specific quantization co-design is used.

Related papers

• Reducing ANN-SNN Conversion Error via Residual Membrane Potential Alignment [52.910770415431244]
  Spiking Neural Networks (SNNs) serve as core architectures for neuromorphic computing.<n>ANN-SNN conversion circumvents issues by reusing well-trained ANN weights for low-latency, energy-efficient inference.<n>Existing conversion schemes suffer from severe accuracy drops at small timesteps, large inference delays and cumulative quantization errors.
  arXiv  Detail & Related papers  (2026-08-14T04:46:03Z)
• SparseKAN: Compressing Kolmogorov--Arnold Networks Across Basis Functions, Neurons, and Bits [6.860988566886594]
  We present textbfSparseKAN, a unified approach that compresses KANs along three complementary axes: basis functions, neurons/channels, and numerical precision.<n>SparseKAN equips the base branch, nonlinear basis branch, and individual basis terms with hierarchical learnable gates trained under a differentiable active-cost objective.
  arXiv  Detail & Related papers  (2026-08-01T20:42:41Z)
• Active Quantum Kernel Acquisition for Gaussian Process Regression [30.032230630492155]
  Recent work on quantum kernel classification has shown that allocating shots non-uniformly across kernel entries can reduce the shot budget required to reach a target accuracy.<n>We extend this idea to Gaussian process (GP) regression, a setting whose downstream quantities (full-spectrum posterior variance, log-determinant, marginal likelihood) couple to kernel error more tightly than the sign-only outputs of classification.<n>We derive three closed-form pair-level sensitivities predictive coupling $|_i_j|$, leave-one-out residual, and marginal-likelihood gradient and plug them into a Neyman-style minimum
  arXiv  Detail & Related papers  (2026-06-27T09:40:20Z)
• YouZhi: Towards High-Concurrency Financial LLMs via Adaptive GQA-to-MLA Transition [78.52944812151664]
  Large language models (LLMs) drive significant financial innovations, yet their deployment is bottlenecked by KV cache memory overhead.<n>We propose YouZhi-LLM, a highly efficient financial LLM empowered by a comprehensive structural transition and training pipeline built on the Huawei Ascend ecosystem.
  arXiv  Detail & Related papers  (2026-06-04T08:44:37Z)
• LoRe: Adaptive Interaction-Evaluation Routing with Per-Step Interaction Budgets for Iterative Graph Solvers [13.286251127911719]
  We introduce LoRe, a training-free, inference-time drop-in wrapper that enforces per-step interaction-evaluation budgeting.<n>Under fully inclusive end-to-end wall-clock accounting, LoRe substantially improves scalability on the Maximum Independent Set (MIS) problem.<n>LoRe achieves a $sim 15times$ speedup at $n=1000$ with a $44times$ memory reduction and competitive tour quality.
  arXiv  Detail & Related papers  (2026-05-27T19:00:57Z)
• Bug or Feature$^2$: Weight Drift, Activation Sparsity and Spikes [53.726365933748134]
  We analyze a negative weight drift induced by the interaction between standard losses and positively biased activation functions.<n>We characterize the sparsity-accuracy tradeoff across 79 configurations and identify a sharp accuracy cliff above $sim$70% activation sparsity.
  arXiv  Detail & Related papers  (2026-05-17T21:29:20Z)
• An Amortized Efficiency Threshold for Comparing Neural and Heuristic Solvers in Combinatorial Optimization [0.0]
  A common critique of neural-optimization solvers is that they are less energy-efficient than CPU metaheuristics.<n>This paper examines the inferential step from "training is expensive" to "neural solvers are net-inefficient"<n>We show that the cumulative-energy ratio between the two solvers tends to a constant strictly below one whenever the network wins per instance.
  arXiv  Detail & Related papers  (2026-05-14T09:39:15Z)
• Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning [4.793059213046564]
  We propose a structural pruning method for SO(3) equivariant atomistic foundation models.<n>The pruning is applied along the channel and order dimensions, with each irreducible representation kept or removed as a complete block.<n>The pruned MACE-MP model outperforms the official from-scratch trained small model on 7 of 9 metrics on the Matbench Discovery leaderboard.
  arXiv  Detail & Related papers  (2026-05-09T11:07:03Z)
• Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs [56.246783503873225]
  This paper revisits the weighted strategy for non-stationary parametric bandits.<n>We propose a simpler weight-based algorithm that is as efficient as window/restart-based algorithms.<n>Our framework can be used to improve regret bounds of other parametric bandits.
  arXiv  Detail & Related papers  (2026-01-03T04:50:21Z)
• R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning [80.104336426172]
  Chain-of-thought (CoT) enhances problem-solving ability of large language models.<n>CoT incurs substantial inference cost due to long autoregressive trajectories.<n>We introduce R-Stitch, a training-free hybrid decoding framework.
  arXiv  Detail & Related papers  (2025-07-23T08:14:36Z)
• Tensor Decomposition Networks for Fast Machine Learning Interatomic Potential Computations [48.46721044282335]
  tensor decomposition networks (TDNs) achieve competitive performance with dramatic speedup in computations.<n>We evaluate TDNs on PubChemQCR, a newly curated molecular relaxation dataset containing 105 million DFT-calculated snapshots.<n>Results show that TDNs achieve competitive performance with dramatic speedup in computations.
  arXiv  Detail & Related papers  (2025-07-01T18:46:27Z)
• Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis [121.9821494461427]
  We show how to significantly reduce the number of neurons required for two-layer ReLU networks. We also prove new lower bounds that improve upon prior work, and that under certain assumptions, are best possible.
  arXiv  Detail & Related papers  (2022-06-26T06:51:31Z)
• NPBDREG: A Non-parametric Bayesian Deep-Learning Based Approach for Diffeomorphic Brain MRI Registration [0.0]
  NPBDREG is a non-optimal framework for unsupervised deformable image registration. It provides improved uncertainty estimates and confidence measures in a theoretically well-parametric and computationally efficient way. It shows a slight improvement in the registration accuracy compared to PrVXM.
  arXiv  Detail & Related papers  (2021-08-15T16:00:06Z)

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.