Enhanced Bayesian Compression via Deep Reinforcement Learning
In this paper, we propose an Enhanced Bayesian Compression method to flexibly compress the deep networks via reinforcement learning. Unlike the existing Bayesian compression method which cannot explicitly enforce quantization weights during training, our method learns flexible codebooks in each layer for an optimal network quantization. To dynamically adjust the state of codebooks, we employ an Actor-Critic network to collaborate with the original deep network. Different from most existing network quantization methods, our EBC does not require re-training procedures after the quantization. Experimental results show that our method obtains low-bit precision with acceptable accuracy drop on MNIST, CIFAR and ImageNet.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep Reinforcement LearningQuantizationreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
COMpression with Bayesian Implicit NEural Representations (COMBINER) is a recent data compression method that addresses a key inefficiency of previous Implicit Neural Representation (INR)-based approaches: it avoids quan…
Data CompressionQuantizationUsing Image Transformations to Learn Network Structure
Many learning tasks require observing a sequence of images and making a decision. In a transportation problem of designing and planning for shipping boxes between nodes, we show how to treat the network of nodes and the …
Image CompressionData Compression with Bayesian Attention Networks
The lossless data compression algorithm based on Bayesian Attention Networks is derived from first principles.
Data CompressionPosterior Coreset Construction with Kernelized Stein Discrepancy for Model-Based Reinforcement Learning
Model-based approaches to reinforcement learning (MBRL) exhibit favorable performance in practice, but their theoretical guarantees in large spaces are mostly restricted to the setting when transition model is Gaussian o…
continuous-controlContinuous ControlModel-based Reinforcement Learningreinforcement-learning+1Training Bayesian Neural Networks with Sparse Subspace Variational Inference
Bayesian neural networks (BNNs) offer uncertainty quantification but come with the downside of substantially increased training and inference costs. Sparse BNNs have been investigated for efficient inference, typically b…
Uncertainty QuantificationVariational Inference