• Corpus ID: 230433922

Learning to Optimize Under Constraints with Unsupervised Deep Neural Networks

  title={Learning to Optimize Under Constraints with Unsupervised Deep Neural Networks},
  author={Seyedrazieh Bayati and Faramarz Jabbarvaziri},
In this paper, we propose a machine learning (ML) method to learn how to solve a generic constrained continuous optimization problem. To the best of our knowledge, the generic methods that learn to optimize, focus on unconstrained optimization problems and those dealing with constrained problems are not easy-to-generalize. This approach is quite useful in optimization tasks where the problem’s parameters constantly change, and require resolving the optimization task per parameter update. In… 

Figures from this paper

Energy-Efficient Cooperative Spectrum Sensing Using Machine Learning Algorithm

A neural network is developed, which involves parameters that are integral to the CSS performance, including a device sleeping rate for each sensor and thresholds used in the energy detection method, and a customized loss function based on the energy consumption of the CSS system and multiple penalty terms reflecting the system requirements.



Combining Reinforcement Learning and Constraint Programming for Combinatorial Optimization

This work proposes a general and hybrid approach, based on DRL and CP, that acts as a bridge between both techniques, and experimentally shows that the framework introduced outperforms the stand-alone RL and CP solutions, while being competitive with industrial solvers.

Learning to optimize: Training deep neural networks for wireless resource management

This work first characterize a class of ‘learnable algorithms’ and then design DNNs to approximate some algorithms of interest in wireless communications, demonstrating the superior ability ofDNNs for approximating two considerably complex algorithms that are designed for power allocation in wireless transmit signal design, while giving orders of magnitude speedup in computational time.

Learning to Optimize: Training Deep Neural Networks for Interference Management

A new learning-based perspective is provided to treat the input and output of an SP algorithm as an unknown nonlinear mapping and use a deep neural network (DNN) to approximate it, which can be accurately approximated by a fully connected DNN.

Spatial Deep Learning for Wireless Scheduling

It is shown that it is possible to bypass the channel estimation stage altogether and to use a deep neural network to produce a near optimal schedule based solely on geographic locations of the transmitters and receivers in the network.

A Deep Learning Framework for Optimization of MISO Downlink Beamforming

A deep learning framework for the optimization of downlink beamforming is proposed based on convolutional neural networks and exploitation of expert knowledge, such as the uplink-downlink duality and the known structure of optimal solutions, paving the way for fast realization of optimal beamforming in multiuser MISO systems.

Learning to Optimize ∗

We consider decision-making by boundedly-rational agents in dynamic stochastic environments. The behavioral primitive is anchored to the shadow price of the state vector. Our agent forecasts the

An approach to solving combinatorial optimization problems using a population of reinforcement learning agents

This paper presents an approach that uses reinforcement learning (RL) algorithms to solve combinatorial optimization problems and shows that the presented RL-agent approach can be used as a basis for global optimization techniques.

Perceptual Losses for Real-Time Style Transfer and Super-Resolution

This work considers image transformation problems, and proposes the use of perceptual loss functions for training feed-forward networks for image transformation tasks, and shows results on image style transfer, where aFeed-forward network is trained to solve the optimization problem proposed by Gatys et al. in real-time.

Semidefinite Relaxation of Quadratic Optimization Problems

In this article, we have provided general, comprehensive coverage of the SDR technique, from its practical deployments and scope of applicability to key theoretical results. We have also showcased

Beamforming Design for Large-Scale Antenna Arrays Using Deep Learning

  • Tian LinY. Zhu
  • Computer Science, Business
    IEEE Wireless Communications Letters
  • 2020
A deep learning based BF design approach is proposed and a BF neural network (BFNN) is developed which can be trained to learn how to optimize the beamformer for maximizing the spectral efficiency with hardware limitation and imperfect CSI.