Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm

• URL: http://arxiv.org/abs/2605.14521v1
• Date: Thu, 14 May 2026 08:05:39 GMT
• Title: Enjoy Your Layer Normalization with the Computational Efficiency of RMSNorm
• Abstract summary: Layer normalization (LN) is a fundamental component in modern deep learning.<n>LN's per-sample centering and scaling introduce non-negligible inference overhead.<n>This paper propose a framework to determine whether an LN in an arbitrary DNN can be replaced by RMSNorm without changing the model function.
• Score: 15.439376229570678
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference overhead. RMSNorm improves efficiency by removing the centering operation, yet this may discard benefits associated with centering. This paper propose a framework to determine whether an LN in an arbitrary DNN can be replaced by RMSNorm without changing the model function. The key idea is to fold LN's centering operation into upstream general linear layers by enforcing zero-mean outputs through the column-centered constraint (CCC) and column-based weight centering (CBWC). We extend the analysis to arbitrary DNNs, define such LNs as foldable LNs, and develop a graph-based detection algorithm. Our analysis shows that many LNs in widely used architectures are foldable, enabling exact inference-time conversion and end-to-end acceleration of 2% to 12% without changing model predictions. Experiments across multiple task families further show that, when exact equivalence is partially broken in practical training settings, our method remains competitive with vanilla LN while improving efficiency.

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)
• Efficient Large Language Model Inference with Neural Block Linearization [51.619870789584525]
  We introduce Neural Block Linearization (NBL), a novel framework for accelerating transformer model inference.<n>NBL replaces self-attention layers with linear approximations derived from Linear Minimum Mean Squared Error estimators.<n>In experiments, NBL achieves notable computational speed-ups while preserving competitive accuracy.
  arXiv  Detail & Related papers  (2025-05-27T12:01:43Z)
• CoRMF: Criticality-Ordered Recurrent Mean Field Ising Solver [4.364088891019632]
  We propose an RNN-based efficient Ising model solver, the Criticality-ordered Recurrent Mean Field (CoRMF) By leveraging the approximated tree structure of the underlying Ising graph, the newly-obtained criticality order enables the unification between variational mean-field and RNN. CoRFM solves the Ising problems in a self-train fashion without data/evidence, and the inference tasks can be executed by directly sampling from RNN.
  arXiv  Detail & Related papers  (2024-03-05T16:55:06Z)
• Benign Overfitting in Deep Neural Networks under Lazy Training [72.28294823115502]
  We show that when the data distribution is well-separated, DNNs can achieve Bayes-optimal test error for classification. Our results indicate that interpolating with smoother functions leads to better generalization.
  arXiv  Detail & Related papers  (2023-05-30T19:37:44Z)
• On Feature Learning in Neural Networks with Global Convergence Guarantees [49.870593940818715]
  We study the optimization of wide neural networks (NNs) via gradient flow (GF) We show that when the input dimension is no less than the size of the training set, the training loss converges to zero at a linear rate under GF. We also show empirically that, unlike in the Neural Tangent Kernel (NTK) regime, our multi-layer model exhibits feature learning and can achieve better generalization performance than its NTK counterpart.
  arXiv  Detail & Related papers  (2022-04-22T15:56:43Z)
• Improving predictions of Bayesian neural nets via local linearization [79.21517734364093]
  We argue that the Gauss-Newton approximation should be understood as a local linearization of the underlying Bayesian neural network (BNN) Because we use this linearized model for posterior inference, we should also predict using this modified model instead of the original one. We refer to this modified predictive as "GLM predictive" and show that it effectively resolves common underfitting problems of the Laplace approximation.
  arXiv  Detail & Related papers  (2020-08-19T12:35:55Z)
• A Neural Network Approach for Online Nonlinear Neyman-Pearson Classification [3.6144103736375857]
  We propose a novel Neyman-Pearson (NP) classifier that is both online and nonlinear as the first time in the literature. The proposed classifier operates on a binary labeled data stream in an online manner, and maximizes the detection power about a user-specified and controllable false positive rate. Our algorithm is appropriate for large scale data applications and provides a decent false positive rate controllability with real time processing.
  arXiv  Detail & Related papers  (2020-06-14T20:00:25Z)
• Controllable Orthogonalization in Training DNNs [96.1365404059924]
  Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1. This paper proposes a computationally efficient and numerically stable orthogonalization method using Newton's iteration (ONI) We show that our method improves the performance of image classification networks by effectively controlling the orthogonality to provide an optimal tradeoff between optimization benefits and representational capacity reduction. We also show that ONI stabilizes the training of generative adversarial networks (GANs) by maintaining the Lipschitz continuity of a network, similar to spectral normalization (
  arXiv  Detail & Related papers  (2020-04-02T10:14:27Z)

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.