Robust Heterogeneous Analog-Digital Computing for Mixture-of-Experts Models with Theoretical Generalization Guarantees

• URL: http://arxiv.org/abs/2603.02633v1
• Date: Tue, 03 Mar 2026 06:00:57 GMT
• Title: Robust Heterogeneous Analog-Digital Computing for Mixture-of-Experts Models with Theoretical Generalization Guarantees
• Abstract summary: Sparse Mixture-of-Experts (MoE) models activate only a small sub-set of experts per input, yet their massive parameter counts lead to substantial memory and energy inefficiency during inference.<n>We propose a retraining-free heterogeneous framework in which noise-sensitive experts are computed digitally while the majority of the experts are executed on AIMC hardware.
• Score: 12.747585022756711
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sparse Mixture-of-Experts (MoE) models enable efficient scalability by activating only a small sub-set of experts per input, yet their massive parameter counts lead to substantial memory and energy inefficiency during inference. Analog in-memory computing (AIMC) offers a promising solution by eliminating frequent data movement between memory and compute units. However, mitigating hardware nonidealities of AIMC typically requires noise-aware retraining, which is infeasible for large MoE models. In this paper, we propose a retraining-free heterogeneous computation framework in which noise-sensitive experts, which are provably identifiable by their maximum neuron norm, are computed digitally while the majority of the experts are executed on AIMC hardware. We further assign densely activated modules, such as attention layers, to digital computation due to their high noise sensitivity despite comprising a small fraction of parameters. Extensive experiments on large MoE language models, including DeepSeekMoE and OLMoE, across multiple benchmark tasks validate the robustness of our approach in maintaining accuracy under analog nonidealities.

Related papers

• MoEMB: Scaling Universal Multimodal Embeddings with Efficient Mixture-of-Experts Models [55.732137666068446]
  Universal multimodal embedding (UME) increasingly demands encoder's capacity for handling a broad range of tasks and modalities.<n>MoEMB scales UME along the expert axis through mixture-of-experts (MoE)<n>MoEMB surpasses TTE-based methods with >4x active parameters, using significantly less computes.
  arXiv  Detail & Related papers  (2026-09-08T12:29:50Z)
• DOT-MoE: Differentiable Optimal Transport for MoEfication [11.183649354845885]
  DOT-MoE is a novel framework that formulates the decomposition of dense layers as a Differentiable Optimal Transport problem.<n>We demonstrate that DOT-MoE significantly outperforms structured pruning, clustering, and random-split baselines.
  arXiv  Detail & Related papers  (2026-06-01T04:19:16Z)
• Mixture-of-Experts Models in Vision: Routing, Optimization, and Generalization [0.0]
  We study MoE behavior in an image classification setting, focusing on predictive performance, expert utilization, and generalization.<n>We compare dense, SoftMoE, and SparseMoE classifier heads on the CIFAR10 dataset under comparable model capacity.<n>Both MoE variants achieve slightly higher validation accuracy than the dense baseline while maintaining balanced expert utilization through regularization.<n>We find that SoftMoE exhibits higher sharpness by these metrics, while Dense and SparseMoE lie in a similar curvature regime, despite all models achieving comparable generalization performance.
  arXiv  Detail & Related papers  (2026-01-21T14:22:25Z)
• Robustness of Mixtures of Experts to Feature Noise [25.939504714529807]
  We show that sparse expert activation acts as a noise filter.<n>We show that sparse expert activation acts as a noise filter.<n> Empirical results on synthetic data and real-world language tasks corroborate the theoretical insights.
  arXiv  Detail & Related papers  (2026-01-21T09:15:48Z)
• ResMoE: Space-efficient Compression of Mixture of Experts LLMs via Residual Restoration [61.579842548990754]
  Mixture-of-Experts (MoE) Transformer, the backbone of multiple phenomenal language models, leverages sparsity by activating only a fraction of model parameters for each input token.<n>We introduce ResMoE, an innovative MoE approximation framework that utilizes Wasserstein barycenter to extract a common expert (barycenter expert) and approximate the residuals between this barycenter expert and the original ones.
  arXiv  Detail & Related papers  (2025-03-10T03:15:54Z)
• DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs [86.76714527437383]
  This paper proposes DSMoE, a novel approach that achieves sparsification by partitioning pre-trained FFN layers into computational blocks.<n>We implement adaptive expert routing using sigmoid activation and straight-through estimators, enabling tokens to flexibly access different aspects of model knowledge.<n>Experiments on LLaMA models demonstrate that under equivalent computational constraints, DSMoE achieves superior performance compared to existing pruning and MoE approaches.
  arXiv  Detail & Related papers  (2025-02-18T02:37:26Z)
• Designing DNNs for a trade-off between robustness and processing performance in embedded devices [1.474723404975345]
  Machine learning-based embedded systems need to be robust against soft errors.<n>This paper investigates the suitability of using bounded AFs to improve model robustness against perturbations.<n>We analyze encoder-decoder fully convolutional models aimed at performing semantic segmentation tasks on hyperspectral images for scene understanding in autonomous driving.
  arXiv  Detail & Related papers  (2024-12-04T19:34:33Z)
• Synergistic Development of Perovskite Memristors and Algorithms for Robust Analog Computing [53.77822620185878]
  We propose a synergistic methodology to concurrently optimize perovskite memristor fabrication and develop robust analog DNNs.<n>We develop "BayesMulti", a training strategy utilizing BO-guided noise injection to improve the resistance of analog DNNs to memristor imperfections.<n>Our integrated approach enables use of analog computing in much deeper and wider networks, achieving up to 100-fold improvements.
  arXiv  Detail & Related papers  (2024-12-03T19:20:08Z)
• SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Experts [49.01990048827639]
  We introduce SEER-MoE, a framework for reducing both the memory footprint and compute requirements of pre-trained MoE models. The first stage involves pruning the total number of experts using a heavy-hitters counting guidance, while the second stage employs a regularization-based fine-tuning strategy to recover accuracy loss. Our empirical studies demonstrate the effectiveness of our method, resulting in a sparse MoEs model optimized for inference efficiency with minimal accuracy trade-offs.
  arXiv  Detail & Related papers  (2024-04-07T22:13:43Z)
• XMoE: Sparse Models with Fine-grained and Adaptive Expert Selection [30.687511115573038]
  tool is a novel MoE designed to enhance both the efficacy and efficiency of sparse MoE models. tool can enhance model performance while decreasing the computation load at MoE layers by over 50% without sacrificing performance.
  arXiv  Detail & Related papers  (2024-02-27T08:18:02Z)
• On Least Square Estimation in Softmax Gating Mixture of Experts [78.3687645289918]
  We investigate the performance of the least squares estimators (LSE) under a deterministic MoE model. We establish a condition called strong identifiability to characterize the convergence behavior of various types of expert functions. Our findings have important practical implications for expert selection.
  arXiv  Detail & Related papers  (2024-02-05T12:31:18Z)
• MoEfication: Conditional Computation of Transformer Models for Efficient Inference [66.56994436947441]
  Transformer-based pre-trained language models can achieve superior performance on most NLP tasks due to large parameter capacity, but also lead to huge computation cost. We explore to accelerate large-model inference by conditional computation based on the sparse activation phenomenon. We propose to transform a large model into its mixture-of-experts (MoE) version with equal model size, namely MoEfication.
  arXiv  Detail & Related papers  (2021-10-05T02:14:38Z)

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.