Sequential Policy Gradient for Adaptive Hyperparameter Optimization

• URL: http://arxiv.org/abs/2506.15051v1
• Date: Wed, 18 Jun 2025 01:21:39 GMT
• Title: Sequential Policy Gradient for Adaptive Hyperparameter Optimization
• Abstract summary: We propose Sequential Policy Gradient modeling (SPG), a novel trajectory generation paradigm for lightweight online hyperparameter optimization.<n>SPG extends the base model with temporary modules, enabling it to generate state-action (padded) trajectories in a single forward pass.<n>Our experiments demonstrate that models gain performance when retrained with SPG on their original datasets and also outperform standard transfer fine-tuning.
• Score: 6.031164586412059
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning is essential for neural architecture search and hyperparameter optimization, but the conventional approaches impede widespread use due to prohibitive time and computational costs. Inspired by DeepSeek-V3 multi-token prediction architecture, we propose Sequential Policy Gradient modeling (SPG), a novel trajectory generation paradigm for lightweight online hyperparameter optimization. In contrast to conventional policy gradient methods, SPG extends the base model with temporary modules, enabling it to generate state-action (padded) trajectories in a single forward pass. Our experiments demonstrate that models gain performance when retrained with SPG on their original datasets and also outperform standard transfer fine-tuning. We evaluate on five datasets spanning computer vision (ImageNet, COCO), natural language processing (GLUE, SQuAD), and audio (SUPERB) to assess the industrial applicability of SPG. The proposed method demonstrates consistent improvements across widely adopted models, achieving performance gains of $+0.2\sim7\%$, with significantly low computational costs. Fully reproducible code and pre-trained models: https://huggingface.co/UniversalAlgorithmic/SPG.

Related papers

• Low-Rank Adaptation Redux for Large Models [41.28925127311434]
  Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models.<n>Despite its empirical success and rapid proliferation of variants, it remains elusive which architectural choices, optimization techniques, and deployment constraints should guide practical method selection.<n>This overview revisits LoRA through the lens of signal processing (SP), bridging modern adapter designs with classical low-rank modeling tools and inverse problems.
  arXiv  Detail & Related papers  (2026-04-23T17:50:23Z)
• Auto-Unrolled Proximal Gradient Descent: An AutoML Approach to Interpretable Waveform Optimization [1.9290392443571385]
  This study explores the combination of automated machine learning (AutoML) with model-based deep unfolding (DU) for optimizing wireless beamforming and waveforms.<n>We convert the iterative gradient descent (PGD) algorithm into a deep neural network, wherein the parameters are learned instead of being predetermined.
  arXiv  Detail & Related papers  (2026-03-18T08:33:25Z)
• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• Efficient Beamforming Optimization for STAR-RIS-Assisted Communications: A Gradient-Based Meta Learning Approach [29.972987396713126]
  STAR-RIS is a promising technology to realize full-space coverage and spectral efficiency in next-generation wireless networks.<n>We develop a gradient-based meta learning (GML) that directly optimization feeds into neural networks, thereby removing the need for pre-training and enabling fast adaptation.
  arXiv  Detail & Related papers  (2025-12-09T16:28:15Z)
• Towards Efficient General Feature Prediction in Masked Skeleton Modeling [59.46799426434277]
  We propose a novel General Feature Prediction framework (GFP) for efficient mask skeleton modeling.<n>Our key innovation is replacing conventional low-level reconstruction with high-level feature prediction that spans from local motion patterns to global semantic representations.
  arXiv  Detail & Related papers  (2025-09-03T18:05:02Z)
• Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning? [45.58422897857411]
  This work explores the use of large language models (LLMs) for hyperparameter optimization by fine-tuning a parameter-efficient version of Code Llama using LoRA.<n>Our approach achieves competitive or superior Root Mean Square Error (RMSE) while substantially reducing computational overhead.<n>Results demonstrate that LLM-based optimization not only rivals established Bayesian methods like Tree-structured Parzen Estimators (TPE) but also accelerates tuning for real-world applications requiring perceptual quality and low-latency processing.
  arXiv  Detail & Related papers  (2025-04-08T13:15:47Z)
• Instruction-Guided Autoregressive Neural Network Parameter Generation [49.800239140036496]
  We propose IGPG, an autoregressive framework that unifies parameter synthesis across diverse tasks and architectures.<n>By autoregressively generating neural network weights' tokens, IGPG ensures inter-layer coherence and enables efficient adaptation across models and datasets.<n>Experiments on multiple datasets demonstrate that IGPG consolidates diverse pretrained models into a single, flexible generative framework.
  arXiv  Detail & Related papers  (2025-04-02T05:50:19Z)
• Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy [104.48511402784763]
  Performance Law for SR models aims to theoretically investigate and model the relationship between model performance and data quality.<n>We propose Approximate Entropy (ApEn) to assess data quality, presenting a more nuanced approach compared to traditional data quantity metrics.
  arXiv  Detail & Related papers  (2024-11-30T10:56:30Z)
• Automatically Learning Hybrid Digital Twins of Dynamical Systems [56.69628749813084]
  Digital Twins (DTs) simulate the states and temporal dynamics of real-world systems. DTs often struggle to generalize to unseen conditions in data-scarce settings. In this paper, we propose an evolutionary algorithm ($textbfHDTwinGen$) to autonomously propose, evaluate, and optimize HDTwins.
  arXiv  Detail & Related papers  (2024-10-31T07:28:22Z)
• Optimization of geological carbon storage operations with multimodal latent dynamic model and deep reinforcement learning [1.8549313085249324]
  This study introduces the multimodal latent dynamic (MLD) model, a deep learning framework for fast flow prediction and well control optimization in GCS. Unlike existing models, the MLD supports diverse input modalities, allowing comprehensive data interactions. The approach outperforms traditional methods, achieving the highest NPV while reducing computational resources by over 60%.
  arXiv  Detail & Related papers  (2024-06-07T01:30:21Z)
• Edge-Efficient Deep Learning Models for Automatic Modulation Classification: A Performance Analysis [0.7428236410246183]
  We investigate optimized convolutional neural networks (CNNs) developed for automatic modulation classification (AMC) of wireless signals. We propose optimized models with the combinations of these techniques to fuse the complementary optimization benefits. The experimental results show that the proposed individual and combined optimization techniques are highly effective for developing models with significantly less complexity.
  arXiv  Detail & Related papers  (2024-04-11T06:08:23Z)
• Model Performance Prediction for Hyperparameter Optimization of Deep Learning Models Using High Performance Computing and Quantum Annealing [0.0]
  We show that integrating model performance prediction with early stopping methods holds great potential to speed up the HPO process of deep learning models. We propose a novel algorithm called Swift-Hyperband that can use either classical or quantum support vector regression for performance prediction.
  arXiv  Detail & Related papers  (2023-11-29T10:32:40Z)
• Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms [88.74308282658133]
  Reization (RP) Policy Gradient Methods (PGMs) have been widely adopted for continuous control tasks in robotics and computer graphics. Recent studies have revealed that, when applied to long-term reinforcement learning problems, model-based RP PGMs may experience chaotic and non-smooth optimization landscapes. We propose a spectral normalization method to mitigate the exploding variance issue caused by long model unrolls.
  arXiv  Detail & Related papers  (2023-10-30T18:43:21Z)
• A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration [11.154086943903696]
  High-Level Synthesis is a solution for fast prototyping application-specific hardware. We propose HLS, for the first time in the literature, graph neural networks that jointly predict acceleration performance and hardware costs. We show that our approach achieves prediction accuracy comparable with that of commonly used simulators.
  arXiv  Detail & Related papers  (2021-11-29T18:17:45Z)
• ParticleAugment: Sampling-Based Data Augmentation [80.44268663372233]
  We propose a particle filtering formulation to find optimal augmentation policies and their schedules during model training. We show that our formulation for automated augmentation reaches promising results on CIFAR-10, CIFAR-100, and ImageNet datasets.
  arXiv  Detail & Related papers  (2021-06-16T10:56:02Z)
• Enhanced data efficiency using deep neural networks and Gaussian processes for aerodynamic design optimization [0.0]
  Adjoint-based optimization methods are attractive for aerodynamic shape design. They can become prohibitively expensive when multiple optimization problems are being solved. We propose a machine learning enabled, surrogate-based framework that replaces the expensive adjoint solver.
  arXiv  Detail & Related papers  (2020-08-15T15:09:21Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.