A Controlled Diagnostic Study of Hardware-Induced Distortions in Hardware-Aware Training

• URL: http://arxiv.org/abs/2605.09416v1
• Date: Sun, 10 May 2026 08:34:55 GMT
• Title: A Controlled Diagnostic Study of Hardware-Induced Distortions in Hardware-Aware Training
• Abstract summary: Hardware-aware training (HAT) is widely used to improve the robustness of neural networks on non-ideal AI accelerators.<n>This paper presents a framework that models hardware non-idealities as structured perturbations of the forward operator.<n>Our results show a clear separation between perturbations that can be compensated by HAT and those that consistently break optimization.
• Score: 2.0411082897313984
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hardware-aware training (HAT) is widely used to improve the robustness of neural networks on non-ideal AI accelerators, such as analog in-memory computing (IMC) systems. However, not all hardware-induced distortions are equally compensable by training. This paper presents a diagnostic framework that models hardware non-idealities as structured perturbations of the forward operator and evaluates their compatibility with gradient-based optimization. We analyze six representative perturbation classes--read noise, variability, drift, stuck-at faults, IR-drop, and ADC discretization--and identify three key diagnostics: gradient expectation consistency, bounded gradient variance, and non-degenerate sensitivity. Our results show a clear separation between perturbations that can be compensated by HAT and those that consistently break optimization. This provides practical guidance for hardware-software co-design, clarifying which non-idealities can be addressed at the training level and which require circuit-, architecture-, or calibration-level mitigation. This study should be interpreted as a controlled empirical analysis under vanilla forward-perturbation HAT, rather than as a universal theory of hardware-aware training.

Related papers

• Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals [83.0127582612634]
  Near-boundary Rescue (NSR) is a minimal, plug-and-play modification that retains out-of-bound tokens to recover lost signals.<n>NSR substantially improves training stability and delivers consistent gains over strong baselines such as DAPO and GSPO.
  arXiv  Detail & Related papers  (2026-05-21T16:45:31Z)
• Mitigating Error Amplification in Fast Adversarial Training [58.74042726356826]
  Fast Adversarial Training (FAT) has proven effective in enhancing model robustness by encouraging networks to learn perturbation-invariant representations.<n>FAT often suffers from catastrophic overfitting (CO), where the model overfits to the training attack and fails to generalize to unseen ones.<n>We propose a Distribution-aware Dynamic Guidance (DDG) strategy that dynamically adjusts both the perturbation budget and supervision signal.
  arXiv  Detail & Related papers  (2026-04-27T11:23:18Z)
• Robust Reasoning and Learning with Brain-Inspired Representations under Hardware-Induced Nonlinearities [7.417780861658929]
  Traditional machine learning depends on high-precision arithmetic and near-ideal hardware assumptions.<n>We propose a hardware-aware optimization framework based on Hyperdimensional Computing (HDC)<n>Our solution enables scalable, energy-efficient intelligent systems capable of classification and reasoning on emerging CIM hardware.
  arXiv  Detail & Related papers  (2026-04-13T21:35:53Z)
• Variational Rectification Inference for Learning with Noisy Labels [74.85528327499662]
  We propose variational rectification inference (VRI) to formulate the adaptive rectification for loss functions.<n>VRI is constructed as a hierarchical Bayes by treating the rectifying vector as a latent variable.<n>By introducing the variational term in VRI, the conditional posterior is estimated accurately and avoids collapsing to a Dirac delta function.
  arXiv  Detail & Related papers  (2026-03-18T01:25:08Z)
• In-memory Training on Analog Devices with Limited Conductance States via Multi-tile Residual Learning [59.091567092071564]
  In-memory training typically requires at least 8-bit conductance states to match digital baselines.<n>Many promising memristive devices such as ReRAM offer only about 4-bit resolution due to fabrication constraints.<n>This paper proposes a emphresidual learning framework that sequentially learns on multiple crossbar tiles to compensate the residual errors.
  arXiv  Detail & Related papers  (2025-10-02T19:44:25Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• Extending Straight-Through Estimation for Robust Neural Networks on Analog CIM Hardware [5.100973962435092]
  We propose a noise-aware training method for analog Compute-In-Memory (CIM) systems.<n>We decouple forward noise simulation from backward gradient computation, enabling noise-aware training with more accurate but computationally intractable noise modeling.<n>Our framework achieves up to 5.3% accuracy improvement on image classification, 0.72 perplexity reduction on text generation, 2.2$times$ speedup in training time, and 37.9% lower peak memory usage.
  arXiv  Detail & Related papers  (2025-08-16T06:53:44Z)
• A Comparative Analysis of Reinforcement Learning and Conventional Deep Learning Approaches for Bearing Fault Diagnosis [0.0]
  Bearing faults in rotating machinery can lead to significant operational disruptions and maintenance costs.<n>Modern methods for bearing fault diagnosis rely heavily on vibration analysis and machine learning techniques.<n>This study explores the feasibility of reinforcement learning (RL) for bearing fault classification tasks in machine condition monitoring.
  arXiv  Detail & Related papers  (2025-06-24T18:06:57Z)
• Learning A Robust RGB-Thermal Detector for Extreme Modality Imbalance [10.189143024910598]
  RGB-Thermal (RGB-T) object detection utilizes thermal infrared (TIR) images to complement RGB data, improving robustness in challenging conditions.<n>Traditional RGB-T detectors assume balanced training data, where both modalities contribute equally.<n>This paper addresses these challenges by proposing a novel base-and-auxiliary detector architecture.
  arXiv  Detail & Related papers  (2025-05-28T09:18:55Z)
• GAQAT: gradient-adaptive quantization-aware training for domain generalization [54.31450550793485]
  We propose a novel Gradient-Adaptive Quantization-Aware Training (GAQAT) framework for DG.<n>Our approach begins by identifying the scale-gradient conflict problem in low-precision quantization.<n>Extensive experiments validate the effectiveness of the proposed GAQAT framework.
  arXiv  Detail & Related papers  (2024-12-07T06:07:21Z)
• Towards Exact Gradient-based Training on Analog In-memory Computing [28.38387901763604]
  Inference on analog accelerators has been studied recently, but the training perspective is underexplored. Recent studies have shown that the "workhorse" of digital AI training - gradient descent (SGD) algorithm converges inexactly when applied to model training on non-ideal devices. This paper puts forth a theoretical foundation for gradient-based training on analog devices.
  arXiv  Detail & Related papers  (2024-06-18T16:43:59Z)
• Analyzing Adversarial Inputs in Deep Reinforcement Learning [53.3760591018817]
  We present a comprehensive analysis of the characterization of adversarial inputs, through the lens of formal verification. We introduce a novel metric, the Adversarial Rate, to classify models based on their susceptibility to such perturbations. Our analysis empirically demonstrates how adversarial inputs can affect the safety of a given DRL system with respect to such perturbations.
  arXiv  Detail & Related papers  (2024-02-07T21:58:40Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)

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.