Data-Driven Upper Bounds on Channel Capacity

• URL: http://arxiv.org/abs/2205.06471v1
• Date: Fri, 13 May 2022 06:59:31 GMT
• Title: Data-Driven Upper Bounds on Channel Capacity
• Authors: Christian H\"ager, Erik Agrell
• Abstract summary: We consider the problem of estimating an upper bound on the capacity of a memoryless channel with unknown alphabet output. A novel-driven algorithm is proposed that exploits dual representation where the minimization over the input distribution is replaced with a reference distribution on the channel output.
• Score: 4.974890682815778
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider the problem of estimating an upper bound on the capacity of a memoryless channel with unknown channel law and continuous output alphabet. A novel data-driven algorithm is proposed that exploits the dual representation of capacity where the maximization over the input distribution is replaced with a minimization over a reference distribution on the channel output. To efficiently compute the required divergence maximization between the conditional channel and the reference distribution, we use a modified mutual information neural estimator that takes the channel input as an additional parameter. We evaluate our approach on different memoryless channels and show that the estimated upper bounds closely converge either to the channel capacity or to best-known lower bounds.

Related papers

• Resolvability of classical-quantum channels [54.825573549226924]
  We study the resolvability of classical-quantum channels in two settings, for the channel output generated from the worst input, and form the fixed independent and identically distributed (i.i.d.) input. For the fixed-input setting, while the direct part follows from the known quantum soft covering result, we exploit the recent alternative quantum Sanov theorem to solve the strong converse.
  arXiv  Detail & Related papers  (2024-10-22T05:18:43Z)
• Maximal-Capacity Discrete Memoryless Channel Identification [37.598696937684245]
  The problem of identifying the channel with the highest capacity among several memoryless channels (DMCs) is considered. A capacity estimator is proposed and tight confidence bounds on the estimator error are derived. A gap-elimination algorithm termed BestChanID is proposed, which is oblivious to the capacity-achieving input distribution. Two additional algorithms NaiveChanSel and MedianChanEl, that output with certain confidence a DMC with capacity close to the maximal, are introduced.
  arXiv  Detail & Related papers  (2024-01-18T18:44:10Z)
• Joint Channel Estimation and Feedback with Masked Token Transformers in Massive MIMO Systems [74.52117784544758]
  This paper proposes an encoder-decoder based network that unveils the intrinsic frequency-domain correlation within the CSI matrix. The entire encoder-decoder network is utilized for channel compression. Our method outperforms state-of-the-art channel estimation and feedback techniques in joint tasks.
  arXiv  Detail & Related papers  (2023-06-08T06:15:17Z)
• Channel Simulation: Finite Blocklengths and Broadcast Channels [13.561997774592667]
  We study channel simulation under common randomness assistance in the finite-blocklength regime. We identify the smooth channel max-information as a linear program one-shot converse on the minimal simulation cost for fixed error tolerance.
  arXiv  Detail & Related papers  (2022-12-22T13:08:55Z)
• Learning to Perform Downlink Channel Estimation in Massive MIMO Systems [72.76968022465469]
  We study downlink (DL) channel estimation in a Massive multiple-input multiple-output (MIMO) system. A common approach is to use the mean value as the estimate, motivated by channel hardening. We propose two novel estimation methods.
  arXiv  Detail & Related papers  (2021-09-06T13:42:32Z)
• Discriminative Mutual Information Estimators for Channel Capacity Learning [1.8275108630751837]
  We propose a novel framework to automatically learn the channel capacity, for any type of memory-less channel. We include the discriminator in a cooperative channel capacity learning framework, referred to as CORTICAL. We prove that a particular choice of cooperative value function solves the channel capacity estimation problem.
  arXiv  Detail & Related papers  (2021-07-07T09:03:40Z)
• Model-Driven Deep Learning Based Channel Estimation and Feedback for Millimeter-Wave Massive Hybrid MIMO Systems [61.78590389147475]
  This paper proposes a model-driven deep learning (MDDL)-based channel estimation and feedback scheme for millimeter-wave (mmWave) systems. To reduce the uplink pilot overhead for estimating the high-dimensional channels from a limited number of radio frequency (RF) chains, we propose to jointly train the phase shift network and the channel estimator as an auto-encoder. Numerical results show that the proposed MDDL-based channel estimation and feedback scheme outperforms the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-04-22T13:34:53Z)
• Deep Learning Based Antenna Selection for Channel Extrapolation in FDD Massive MIMO [54.54508321463112]
  In massive multiple-input multiple-output (MIMO) systems, the large number of antennas would bring a great challenge for the acquisition of the accurate channel state information. We utilize the neural networks (NNs) to capture the inherent connection between the uplink and downlink channel data sets and extrapolate the downlink channels from a subset of the uplink channel state information. We study the antenna subset selection problem in order to achieve the best channel extrapolation and decrease the data size of NNs.
  arXiv  Detail & Related papers  (2020-09-03T13:38:52Z)
• Operation-Aware Soft Channel Pruning using Differentiable Masks [51.04085547997066]
  We propose a data-driven algorithm, which compresses deep neural networks in a differentiable way by exploiting the characteristics of operations. We perform extensive experiments and achieve outstanding performance in terms of the accuracy of output networks.
  arXiv  Detail & Related papers  (2020-07-08T07:44:00Z)
• Capacity of Continuous Channels with Memory via Directed Information Neural Estimator [15.372626012233736]
  This work proposes a novel capacity estimation algorithm that treats the channel as a blackbox' The algorithm has two main ingredients: (i) a neural distribution transformer (NDT) model that shapes a noise variable into the channel input distribution, and (ii) the neural DI estimator (DINE) that estimates the communication rate of the current NDT model.
  arXiv  Detail & Related papers  (2020-03-09T14:53:56Z)

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.