Beyond $\ell_2$-norm and $\ell_\infty$-norm: A Curvature-Inspired $\ell_p$-Norm Scheme for Deep Neural Networks

• URL: http://arxiv.org/abs/2606.02078v1
• Date: Mon, 01 Jun 2026 11:07:35 GMT
• Title: Beyond $\ell_2$-norm and $\ell_\infty$-norm: A Curvature-Inspired $\ell_p$-Norm Scheme for Deep Neural Networks
• Abstract summary: We propose a $ell_p$-norm scheme with a dynamical value of $p$ and incorporate it into a gradient descent (SGD) and momentum (SGDM)<n>We establish theoretical guarantees resulting in LPSGD and LPSGDM that achieve an (O-1/2) convergence rate for deep neural networks.
• Score: 23.324496414025322
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The existing optimizers for deep neural networks (DNNs) typically rely on either the $\ell_2$ norm or the $\ell_\infty$ norm, resulting in optimizers that do not adapt well to substantial changes in curvature across parameter dimensions. Generally, the training process of DNNs often exhibits strong curvature anisotropy in the early period, whereas in the later period, the training process of DNNs tends to move toward flatter regions with weaker anisotropy. Particularly, optimizers based on the \(\ell_2\)-norm are usually dominated by high-curvature directions, restricting updates of optimizers along with lower curvature direction and thus leading to a slower convergence rate. While optimizers based on the \(\ell_\infty\)-norm are prone to oscillations in flatter regions, due to the coordinate-wise updates of the same magnitude. To address these two extreme cases generated by $\ell_2$ and $\ell_\infty$ norms, we propose a novel $\ell_p$-norm scheme with a dynamical value of $p$ and incorporate it into stochastic gradient descent (SGD) and SGD with momentum (SGDM), leading to two novel optimizers with better generalization performance: ${\ell_p}$-SGD (LPSGD) and ${\ell_p}$-SGDM (LPSGDM). Particularly, the resulting optimizers suppress the dominance of high-curvature directions in the early period by utilizing a large $p$ ($p>2$), followed by a gradual decrease of $p$ toward 2 to enable more stable and refined updates, where the latter process is motivated by the cosine annealing strategy. We establish theoretical guarantees of the resulting algorithms and analyze that both LPSGD and LPSGDM achieve an \(O(T^{-1/2})\) convergence rate for the nonconvex setting. Extensive experiments are conducted on benchmark datasets, including CIFAR-10, CIFAR-100, and ImageNet-1K, with multiple DNNs such as VGG-11, ResNet-18, and ResNet-50.

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)
• Scale-Invariant Neural Network Optimization: Norm Geometry and Heavy-Tailed Noise [12.977441534320041]
  We show that a scale-invariant first-order method with spectral norm requires $(minm, n-frac3p-2p-1) calls.<n>We prove that a batched method achieves the matching bound of $(minm, n-frac5p2p-2p-2)$ when the norm is spectral and the Hessian is Lipschitz.
  arXiv  Detail & Related papers  (2026-05-18T15:13:18Z)
• Evolution Strategies at the Hyperscale [57.75314521465674]
  We introduce EGGROLL, an evolution strategies (ES) algorithm designed to scale backprop-free optimization to large population sizes.<n>ES is a set of powerful blackbox optimisation methods that can handle non-differentiable or noisy objectives.<n>EGGROLL overcomes these bottlenecks by generating random matrices $Ain mathbbRmtimes r, Bin mathbbRntimes r$ with $rll min(m,n)$ to form a low-rank matrix perturbation $A Btop$
  arXiv  Detail & Related papers  (2025-11-20T18:56:05Z)
• AdamHD: Decoupled Huber Decay Regularization for Language Model Pre-Training [0.2578242050187029]
  AdamHuberDecay is a drop-in replacement for AdamW that substitutes the $ell$ penalty with a decoupled smooth Huber regularizer.<n>Experiments on GPT-2 and GPT-3 pre-training demonstrate that AdamHuberDecay converges 10-15% faster in wall-clock time.
  arXiv  Detail & Related papers  (2025-11-18T18:08:20Z)
• Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization [22.883367233817836]
  We show that $D$-Gating is theoretically equivalent to solving the original group sparsity problem.<n>We validate our theory across vision, language, and tasks, where $D$-Gating consistently delivers strong performance-sparsity tradeoffs.
  arXiv  Detail & Related papers  (2025-09-28T14:08:29Z)
• FedSVD: Adaptive Orthogonalization for Private Federated Learning with LoRA [68.44043212834204]
  Low-Rank Adaptation (LoRA) is widely used for efficient fine-tuning of language models in learning (FL)<n>Low-Rank Adaptation (LoRA) is widely used for efficient fine-tuning of language models in learning (FL)
  arXiv  Detail & Related papers  (2025-05-19T07:32:56Z)
• Efficient k-Nearest-Neighbor Machine Translation with Dynamic Retrieval [49.825549809652436]
  $k$NN-MT constructs an external datastore to store domain-specific translation knowledge. adaptive retrieval ($k$NN-MT-AR) dynamically estimates $lambda$ and skips $k$NN retrieval if $lambda$ is less than a fixed threshold. We propose dynamic retrieval ($k$NN-MT-DR) that significantly extends vanilla $k$NN-MT in two aspects.
  arXiv  Detail & Related papers  (2024-06-10T07:36:55Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Decoupled Weight Decay for Any $p$ Norm [1.1510009152620668]
  We consider a simple yet effective approach to sparsification, based on the Bridge, $L_p$ regularization during training. We introduce a novel weight decay scheme, which generalizes the standard $L$ weight decay to any $p$ norm. We empirically demonstrate that it leads to highly sparse networks, while maintaining performance comparable to standard $L$ regularization.
  arXiv  Detail & Related papers  (2024-04-16T18:02:15Z)
• Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization [94.06564567766475]
  DP-SGD and DP-NSGD mitigate the risk of large models memorizing sensitive training data. We show that these two algorithms achieve similar best accuracy while DP-NSGD is comparatively easier to tune than DP-SGD.
  arXiv  Detail & Related papers  (2022-06-27T03:45:02Z)
• 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)
• Improve the Robustness and Accuracy of Deep Neural Network with $L_{2,\infty}$ Normalization [0.0]
  The robustness and accuracy of the deep neural network (DNN) was enhanced by introducing the $L_2,infty$ normalization. It is proved that the $L_2,infty$ normalization leads to large dihedral angles between two adjacent faces of the polyhedron graph of the DNN function.
  arXiv  Detail & Related papers  (2020-10-10T05:45:45Z)

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.