Robustness of Mixtures of Experts to Feature Noise

• URL: http://arxiv.org/abs/2601.14792v1
• Date: Wed, 21 Jan 2026 09:15:48 GMT
• Title: Robustness of Mixtures of Experts to Feature Noise
• Abstract summary: 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.
• Score: 25.939504714529807
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite their practical success, it remains unclear why Mixture of Experts (MoE) models can outperform dense networks beyond sheer parameter scaling. We study an iso-parameter regime where inputs exhibit latent modular structure but are corrupted by feature noise, a proxy for noisy internal activations. We show that sparse expert activation acts as a noise filter: compared to a dense estimator, MoEs achieve lower generalization error under feature noise, improved robustness to perturbations, and faster convergence speed. Empirical results on synthetic data and real-world language tasks corroborate the theoretical insights, demonstrating consistent robustness and efficiency gains from sparse modular computation.

Related papers

• Should All Noises Be Treated Equally: Impact of Input Noise Variability on Neural Network Robustness [0.5188499345298442]
  Deep learning is highly sensitive to the nature of training noise, especially under out-of-distribution conditions.<n>This study investigates the influence of noise parameters, such as type, scale, and complexity on the performance, generalization and robustness of neural networks.
  arXiv  Detail & Related papers  (2026-09-13T13:30:37Z)
• Robust Heterogeneous Analog-Digital Computing for Mixture-of-Experts Models with Theoretical Generalization Guarantees [12.747585022756711]
  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.
  arXiv  Detail & Related papers  (2026-03-03T06:00:57Z)
• AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Condition [72.24180896265192]
  We introduce AgentNoiseBench, a framework for evaluating robustness of agentic models under noisy environments.<n>We first conduct an in-depth analysis of biases and uncertainties in real-world scenarios.<n>We then categorize environmental noise into two primary types: user-noise and tool-noise.<n>Building on this analysis, we develop an automated pipeline that injects controllable noise into existing agent-centric benchmarks.
  arXiv  Detail & Related papers  (2026-02-11T20:33:10Z)
• 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)
• Noise-Robust Tiny Object Localization with Flows [63.60972031108944]
  We propose a noise-robust localization framework leveraging normalizing flows for flexible error modeling and uncertainty-guided optimization.<n>Our method captures complex, non-Gaussian prediction distributions through flow-based error modeling, enabling robust learning under noisy supervision.<n>An uncertainty-aware gradient modulation mechanism further suppresses learning from high-uncertainty, noise-prone samples, mitigating overfitting while stabilizing training.
  arXiv  Detail & Related papers  (2026-01-02T09:16:55Z)
• Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models [57.49136894315871]
  New paradigm of test-time scaling has yielded remarkable breakthroughs in reasoning models and generative vision models.<n>We propose one solution to the problem of integrating test-time scaling knowledge into a model during post-training.<n>We replace reward guided test-time noise optimization in diffusion models with a Noise Hypernetwork that modulates initial input noise.
  arXiv  Detail & Related papers  (2025-08-13T17:33:37Z)
• Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE [19.187321201355747]
  Current fine-tuning methods for adapting pre-trained language models to downstream tasks are susceptible to interference from noisy data.<n>We propose a noise-robust adaptation method via asymmetric LoRA poisoning experts (LoPE)<n>LoPE achieves strong performance and robustness purely through the low-cost noise injection, which completely eliminates the requirement of data cleaning.
  arXiv  Detail & Related papers  (2025-05-29T10:35:07Z)
• Triply Laplacian Scale Mixture Modeling for Seismic Data Noise Suppression [51.87076090814921]
  Sparsity-based tensor recovery methods have shown great potential in suppressing seismic data noise.<n>We propose a novel triply Laplacian scale mixture (TLSM) approach for seismic data noise suppression.
  arXiv  Detail & Related papers  (2025-02-20T08:28:01Z)
• 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)
• The Missing U for Efficient Diffusion Models [3.712196074875643]
  Diffusion Probabilistic Models yield record-breaking performance in tasks such as image synthesis, video generation, and molecule design. Despite their capabilities, their efficiency, especially in the reverse process, remains a challenge due to slow convergence rates and high computational costs. We introduce an approach that leverages continuous dynamical systems to design a novel denoising network for diffusion models.
  arXiv  Detail & Related papers  (2023-10-31T00:12:14Z)
• Walking Noise: On Layer-Specific Robustness of Neural Architectures against Noisy Computations and Associated Characteristic Learning Dynamics [1.5184189132709105]
  We discuss the implications of additive, multiplicative and mixed noise for different classification tasks and model architectures. We propose a methodology called Walking Noise which injects layer-specific noise to measure the robustness. We conclude with a discussion of the use of this methodology in practice, among others, discussing its use for tailored multi-execution in noisy environments.
  arXiv  Detail & Related papers  (2022-12-20T17:09:08Z)
• Multiplicative noise and heavy tails in stochastic optimization [62.993432503309485]
  empirical optimization is central to modern machine learning, but its role in its success is still unclear. We show that it commonly arises in parameters of discrete multiplicative noise due to variance. A detailed analysis is conducted in which we describe on key factors, including recent step size, and data, all exhibit similar results on state-of-the-art neural network models.
  arXiv  Detail & Related papers  (2020-06-11T09:58:01Z)

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.