Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning

• URL: http://arxiv.org/abs/2604.22838v1
• Date: Tue, 21 Apr 2026 06:27:18 GMT
• Title: Neural Network Optimization Reimagined: Decoupled Techniques for Scratch and Fine-Tuning
• Abstract summary: We propose DualOpt, a novel approach that decouples optimization techniques specifically tailored for training from scratch.<n>For training from scratch, we introduce real-time layer-wise weight decay, designed to enhance both convergence and generalization.<n>We extend the layer-wise weight decay to dynamically adjust the rollback levels across layers, adapting to the varying demands of different downstream tasks.
• Score: 49.751529745537546
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the accumulation of resources in the era of big data and the rise of pre-trained models in deep learning, optimizing neural networks for various tasks often involves different strategies for fine-tuning pre-trained models versus training from scratch. However, existing optimizers primarily focus on reducing the loss function by updating model parameters, without fully addressing the unique demands of these two major paradigms. In this paper, we propose DualOpt, a novel approach that decouples optimization techniques specifically tailored for these distinct training scenarios. For training from scratch, we introduce real-time layer-wise weight decay, designed to enhance both convergence and generalization by aligning with the characteristics of weight updates and network architecture. For more importantly fine-tuning, we integrate weight rollback with the optimizer, incorporating a rollback term into each weight update step. This ensures consistency in the weight distribution between upstream and downstream models, effectively mitigating knowledge forgetting and improving fine-tuning performance. Additionally, we extend the layer-wise weight decay to dynamically adjust the rollback levels across layers, adapting to the varying demands of different downstream tasks. Extensive experiments across diverse tasks, including image classification, object detection, semantic segmentation, and instance segmentation, demonstrate the broad applicability and state-of-the-art performance of DualOpt. Code is available at https://github.com/qklee-lz/OLOR-AAAI-2024.

Related papers

• Geometric Self-Supervised Pre-training for Neural Combinatorial Optimization [40.74618635552097]
  We propose a geometric self-supervised pre-training framework for routing graphs.<n>The framework learns robust structural representations prior to the policy optimization phase.<n>The proposed model exhibits remarkable computational efficiency, delivering speedups of up to two orders of magnitude over the exact solver Concorde.
  arXiv  Detail & Related papers  (2026-07-31T20:23:21Z)
• Input Conditioned Layer Dropping in Speech Foundation Models [11.05223262950967]
  layer dropping ($mathcalLD$) skips fraction of the layers of a backbone network during inference to reduce the computational load.<n>We propose input-driven $mathcalLD$ that employs the network's input features and a lightweight layer selecting network to determine optimum combination of processing layers.
  arXiv  Detail & Related papers  (2025-07-10T17:39:03Z)
• Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration [100.54419875604721]
  All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. We propose DyNet, a dynamic family of networks designed in an encoder-decoder style for all-in-one image restoration tasks. Our DyNet can seamlessly switch between its bulkier and lightweight variants, thereby offering flexibility for efficient model deployment.
  arXiv  Detail & Related papers  (2024-04-02T17:58:49Z)
• FOSTER: Feature Boosting and Compression for Class-Incremental Learning [52.603520403933985]
  Deep neural networks suffer from catastrophic forgetting when learning new categories. We propose a novel two-stage learning paradigm FOSTER, empowering the model to learn new categories adaptively.
  arXiv  Detail & Related papers  (2022-04-10T11:38:33Z)
• EvoPruneDeepTL: An Evolutionary Pruning Model for Transfer Learning based Deep Neural Networks [15.29595828816055]
  We propose an evolutionary pruning model for Transfer Learning based Deep Neural Networks. EvoPruneDeepTL replaces the last fully-connected layers with sparse layers optimized by a genetic algorithm. Results show the contribution of EvoPruneDeepTL and feature selection to the overall computational efficiency of the network.
  arXiv  Detail & Related papers  (2022-02-08T13:07:55Z)
• Joint inference and input optimization in equilibrium networks [68.63726855991052]
  deep equilibrium model is a class of models that foregoes traditional network depth and instead computes the output of a network by finding the fixed point of a single nonlinear layer. We show that there is a natural synergy between these two settings. We demonstrate this strategy on various tasks such as training generative models while optimizing over latent codes, training models for inverse problems like denoising and inpainting, adversarial training and gradient based meta-learning.
  arXiv  Detail & Related papers  (2021-11-25T19:59:33Z)
• Powerpropagation: A sparsity inducing weight reparameterisation [65.85142037667065]
  We introduce Powerpropagation, a new weight- parameterisation for neural networks that leads to inherently sparse models. Models trained in this manner exhibit similar performance, but have a distribution with markedly higher density at zero, allowing more parameters to be pruned safely. Here, we combine Powerpropagation with a traditional weight-pruning technique as well as recent state-of-the-art sparse-to-sparse algorithms, showing superior performance on the ImageNet benchmark.
  arXiv  Detail & Related papers  (2021-10-01T10:03:57Z)
• A Differential Game Theoretic Neural Optimizer for Training Residual Networks [29.82841891919951]
  We propose a generalized Differential Dynamic Programming (DDP) neural architecture that accepts both residual connections and convolution layers. The resulting optimal control representation admits a gameoretic perspective, in which training residual networks can be interpreted as cooperative trajectory optimization on state-augmented systems.
  arXiv  Detail & Related papers  (2020-07-17T10:19:17Z)
• Dynamic Hierarchical Mimicking Towards Consistent Optimization Objectives [73.15276998621582]
  We propose a generic feature learning mechanism to advance CNN training with enhanced generalization ability. Partially inspired by DSN, we fork delicately designed side branches from the intermediate layers of a given neural network. Experiments on both category and instance recognition tasks demonstrate the substantial improvements of our proposed method.
  arXiv  Detail & Related papers  (2020-03-24T09:56:13Z)

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.