Element-wise Modulation of Random Matrices for Efficient Neural Layers

• URL: http://arxiv.org/abs/2512.13480v1
• Date: Mon, 15 Dec 2025 16:16:53 GMT
• Title: Element-wise Modulation of Random Matrices for Efficient Neural Layers
• Authors: Maksymilian Szorc,
• Abstract summary: We propose a novel approach that decouples feature mixing from adaptation by utilizing a fixed random matrix modulated by lightweight, learnable element-wise parameters.<n>This architecture drastically reduces the trainable parameter count to a linear scale while retaining reliable accuracy across various benchmarks.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Fully connected layers are a primary source of memory and computational overhead in deep neural networks due to their dense, often redundant parameterization. While various compression techniques exist, they frequently introduce complex engineering trade-offs or degrade model performance. We propose the Parametrized Random Projection (PRP) layer, a novel approach that decouples feature mixing from adaptation by utilizing a fixed random matrix modulated by lightweight, learnable element-wise parameters. This architecture drastically reduces the trainable parameter count to a linear scale while retaining reliable accuracy across various benchmarks. The design serves as a stable, computationally efficient solution for architectural scaling and deployment in resource-limited settings.

Related papers

• GRASP: GRouped Activation Shared Parameterization for Parameter-Efficient Fine-Tuning and Robust Inference of Transformers [12.475144734899674]
  We introduce GRASP, a lightweight PEFT framework that partitions the D-dimensional token representations of selected layers into K D groups and learns a shared scaling and shifting vector for each group.<n>We propose StochGRASP, which learns Gaussian distributions as perturbations to the pre-trained weights rather than deterministic values.<n>Under varying levels of noise, StochGRASP consistently outperforms deterministic variants, demonstrating its suitability for energy-efficient and noise-prone hardware platforms.
  arXiv  Detail & Related papers  (2025-12-03T22:17:05Z)
• QR-LoRA: Efficient and Disentangled Fine-tuning via QR Decomposition for Customized Generation [52.024845354511555]
  We propose QR-LoRA, a novel fine-tuning framework leveraging QR decomposition for structured parameter updates.<n>Our key insight is that the Q matrix naturally minimizes interference between different visual features.<n>Experiments demonstrate that QR-LoRA achieves superior disentanglement in content-style fusion tasks.
  arXiv  Detail & Related papers  (2025-07-07T01:31:01Z)
• Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations [50.010924231754856]
  Adapting pre-trained foundation models for diverse downstream tasks is a core practice in artificial intelligence.<n>To overcome this, parameter-efficient fine-tuning (PEFT) methods like LoRA have emerged and are becoming a growing research focus.<n>We propose a generalization that extends matrix-based PEFT methods to higher-dimensional parameter spaces without compromising their structural properties.
  arXiv  Detail & Related papers  (2025-04-01T14:36:45Z)
• Adaptive Error-Bounded Hierarchical Matrices for Efficient Neural Network Compression [0.0]
  This paper introduces a dynamic, error-bounded hierarchical matrix (H-matrix) compression method tailored for Physics-Informed Neural Networks (PINNs) The proposed approach reduces the computational complexity and memory demands of large-scale physics-based models while preserving the essential properties of the Neural Tangent Kernel (NTK) Empirical results demonstrate that this technique outperforms traditional compression methods, such as Singular Value Decomposition (SVD), pruning, and quantization, by maintaining high accuracy and improving generalization capabilities.
  arXiv  Detail & Related papers  (2024-09-11T05:55:51Z)
• Multilevel CNNs for Parametric PDEs based on Adaptive Finite Elements [0.0]
  A neural network architecture is presented that exploits the multilevel properties of high-dimensional parameter-dependent partial differential equations. The network is trained with data on adaptively refined finite element meshes. A complete convergence and complexity analysis is carried out for the adaptive multilevel scheme.
  arXiv  Detail & Related papers  (2024-08-20T13:32:11Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Scaling Pre-trained Language Models to Deeper via Parameter-efficient Architecture [68.13678918660872]
  We design a more capable parameter-sharing architecture based on matrix product operator (MPO) MPO decomposition can reorganize and factorize the information of a parameter matrix into two parts. Our architecture shares the central tensor across all layers for reducing the model size.
  arXiv  Detail & Related papers  (2023-03-27T02:34:09Z)
• Neural Implicit Flow: a mesh-agnostic dimensionality reduction paradigm of spatio-temporal data [4.996878640124385]
  We propose a general framework called Neural Implicit Flow (NIF) that enables a mesh-agnostic, low-rank representation of large-scale, parametric, spatialtemporal data. NIF consists of two modified multilayer perceptrons (i) ShapeNet, which isolates and represents the spatial complexity (i) ShapeNet, which accounts for any other input measurements, including parametric dependencies, time, and sensor measurements. We demonstrate the utility of NIF for parametric surrogate modeling, enabling the interpretable representation and compression of complex spatial-temporal dynamics, efficient many-spatial-temporal generalization, and improved performance for sparse
  arXiv  Detail & Related papers  (2022-04-07T05:02:58Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• Joint Deep Reinforcement Learning and Unfolding: Beam Selection and Precoding for mmWave Multiuser MIMO with Lens Arrays [54.43962058166702]
  millimeter wave (mmWave) multiuser multiple-input multiple-output (MU-MIMO) systems with discrete lens arrays have received great attention. In this work, we investigate the joint design of a beam precoding matrix for mmWave MU-MIMO systems with DLA.
  arXiv  Detail & Related papers  (2021-01-05T03:55:04Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)

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.