Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization

• URL: http://arxiv.org/abs/2606.26002v1
• Date: Wed, 24 Jun 2026 16:19:29 GMT
• Title: Hierarchical Reinforcement Learning for Neural Network Compression (HiReLC): Pruning and Quantization
• Abstract summary: HiReLC is a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks.<n>Low-level agents (LLAs) operate independently per block, selecting per- Kernel configurations over a multi-discrete action space.<n>High-level agents (HLAs) coordinate global budget allocation via ensemble voting guided by Fisher Information-based sensitivity estimates.
• Score: 1.7616042687330635
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks. The framework decomposes the compression search across two levels of abstraction: low-level agents (LLAs) operate independently per block, selecting per-kernel configurations over a multi-discrete action space spanning bitwidth, pruning keep-ratio, quantization type, and granularity, while high-level agents (HLAs) coordinate global budget allocation via ensemble voting guided by Fisher Information-based sensitivity estimates. To mitigate the computational cost of policy evaluation, an iterative active learning loop interleaves surrogate-guided RL optimization with post-compression fine-tuning, using a lightweight MLP surrogate to amortize expensive evaluations and a logit-MSE proxy during cold-start. The surrogate is used for reward shaping rather than as a replacement for final post-compression evaluation. The controller is architecture-agnostic by design, with a modular layer abstraction decoupling the RL environment from the underlying network topology. Experiments across Vision Transformer and CNN benchmarks demonstrate effective parameter-storage compression ratios of 5.99 - 6.72$\times$ with a 3.83 % gain in one setting and 0.55 - 5.62 % accuracy drops elsewhere, supporting hierarchical policy decomposition and sensitivity-aware guidance as practical design choices for joint neural network compression.

Related papers

• GO-GenZip: Goal-Oriented Generative Sampling and Hybrid Compression [50.76941829813458]
  Current network data telemetry pipelines consist of massive streams of fine-grained Key Performance Indicators (KPIs) from multiple distributed sources towards central aggregators.<n>This work presents a generative AI (GenAI)-driven sampling and hybrid compression framework that redesigns network telemetry from a goal-oriented perspective.
  arXiv  Detail & Related papers  (2026-03-20T16:33:15Z)
• HQP: Sensitivity-Aware Hybrid Quantization and Pruning for Ultra-Low-Latency Edge AI Inference [0.0]
  Hybrid Quantization and Pruning (HQP) framework designed to achieve synergistic model acceleration.<n>HQP framework achieves a peak performance gain of 3.12 times inference speedup and a 55 percent model size reduction.
  arXiv  Detail & Related papers  (2026-02-02T18:17:45Z)
• Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation [75.58269386927076]
  Autoregressive (AR) models are often dismissed as impractical due to prohibitive computational cost.<n>This work re-thinks this paradigm, introducing a framework built on hierarchical parallelism and progressive adaptation.<n> Experiments on diverse datasets (natural, satellite, medical) validate that our method achieves new state-of-the-art compression.
  arXiv  Detail & Related papers  (2025-11-14T06:27:58Z)
• Structure-Aware Automatic Channel Pruning by Searching with Graph Embedding [28.03880549472142]
  Channel pruning is a powerful technique to reduce the computational overhead of deep neural networks.<n>We propose a novel structure-aware automatic channel pruning (SACP) framework to model the network topology and learn the global importance of each channel.<n>SACP outperforms state-of-the-art pruning methods on compression efficiency and competitive on accuracy retention.
  arXiv  Detail & Related papers  (2025-06-13T05:05:35Z)
• An Adaptive Tensor-Train Decomposition Approach for Efficient Deep Neural Network Compression [4.869958813908807]
  We introduce a novel, automatic, and budget-aware rank selection method for efficient model compression.<n> Layer-Wise Imprinting Quantitation (LWIQ) quantifies each layer's significance within a neural network by integrating a proxy classifier.<n> Experimental results on the CIFAR-10 dataset show that our LWIQ improved by 63.2% in rank search efficiency.
  arXiv  Detail & Related papers  (2024-08-02T18:47:11Z)
• An Adaptive Device-Edge Co-Inference Framework Based on Soft Actor-Critic [72.35307086274912]
  High-dimension parameter model and large-scale mathematical calculation restrict execution efficiency, especially for Internet of Things (IoT) devices. We propose a new Deep Reinforcement Learning (DRL)-Soft Actor Critic for discrete (SAC-d), which generates the emphexit point, emphexit point, and emphcompressing bits by soft policy iterations. Based on the latency and accuracy aware reward design, such an computation can well adapt to the complex environment like dynamic wireless channel and arbitrary processing, and is capable of supporting the 5G URL
  arXiv  Detail & Related papers  (2022-01-09T09:31:50Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• 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)
• ALF: Autoencoder-based Low-rank Filter-sharing for Efficient Convolutional Neural Networks [63.91384986073851]
  We propose the autoencoder-based low-rank filter-sharing technique technique (ALF) ALF shows a reduction of 70% in network parameters, 61% in operations and 41% in execution time, with minimal loss in accuracy.
  arXiv  Detail & Related papers  (2020-07-27T09:01:22Z)

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.