Searcharxiv⌕ Search

arXiv subjects

Alexandre Graell i Amat

Publications and source records attributed to Alexandre Graell i Amat.

At least 73 records · Page 4Linked to original sources
arXiv2021

Rateless Codes for Low-Latency Distributed Inference in Mobile Edge Computing

We consider a mobile edge computing scenario where users want to perform a linear inference operation $\boldsymbol{W} \boldsymbol{x}$ on local data $\boldsymbol{x}$ for some network-side matrix $\boldsymbol{W}$. The inference is performed in a distributed fashion over multiple servers at the network edge. For this scenario, we propose a coding scheme that combines a rateless code to provide resiliency against straggling servers--hence reducing the computation latency--and an irregular-repetition code to provide spatial diversity--hence reducing the communication latency. We further derive a lower bound on the total latency--comprising computation latency, communication latency, and decoding latency. The proposed scheme performs remarkably close to the bound and yields significantly lower latency than the scheme based on maximum distance separable codes recently proposed by Zhang and Simeone.

cs.IT↗
arXiv2021

Successive Cancellation Decoding of Single Parity-Check Product Codes: Analysis and Improved Decoding

A product code with single parity-check component codes can be described via the tools of a multi-kernel polar code, where the rows of the generator matrix are chosen according to the constraints imposed by the product code construction. Following this observation, successive cancellation decoding of such codes is introduced. In particular, the error probability of single parity-check product codes over binary memoryless symmetric channels under successive cancellation decoding is characterized. A bridge with the analysis of product codes introduced by Elias is also established for the binary erasure channel. Successive cancellation list decoding of single parity-check product codes is then described. For the provided example, simulations over the binary input additive white Gaussian channel show that successive cancellation list decoding outperforms belief propagation decoding applied to the code graph. Finally, the performance of the concatenation of a product code with a high-rate outer code is investigated via distance spectrum analysis. Examples of concatenations performing within $0.7$ dB from the random coding union bound are provided.

cs.IT↗
arXiv2021

Over-the-fiber Digital Predistortion Using Reinforcement Learning

We demonstrate, for the first time, experimental over-the-fiber training of transmitter neural networks (NNs) using reinforcement learning. Optical back-to-back training of a novel NN-based digital predistorter outperforms arcsine-based predistortion with up to 60\% bit-error-rate reduction.

eess.SP↗
arXiv2021

Generalized Spatially Coupled Parallel Concatenated Convolutional Codes With Partial Repetition

We introduce generalized spatially coupled parallel concatenated codes (GSC-PCCs), a class of spatially coupled turbo-like codes obtained by coupling parallel concatenated codes (PCCs) with a fraction of information bits repeated before the PCC encoding. GSC-PCCs can be seen as a generalization of the original spatially coupled parallel concatenated convolutional codes (SC-PCCs) proposed by Moloudi et al. [1]. To characterize the asymptotic performance of GSC-PCCs, we derive the corresponding density evolution equations and compute their decoding thresholds. We show that the proposed codes have some nice properties such as threshold saturation and that their decoding thresholds improve with the repetition factor $q$. Most notably, our analysis suggests that the proposed codes asymptotically approach the capacity as $q$ tends to infinity with any given constituent convolutional code.

cs.IT↗
arXiv2021

On Doped SC-LDPC Codes for Streaming

In streaming applications, doping improves the performance of spatially-coupled low-density parity-check (SC-LDPC) codes by creating reduced-degree check nodes in the coupled chain. We formulate a scaling law to predict the bit and block error rate of periodically-doped semi-infinite SC-LDPC code ensembles streamed over the binary erasure channel under sliding window decoding for a given finite component block length. The scaling law assumes that with some probability doping is equivalent to full termination and triggers two decoding waves; otherwise, decoding performs as if the coupled chain had not been doped at all. We approximate that probability and use the derived scaling laws to predict the error rates of SC-LDPC code ensembles in the presence of doping. The proposed scaling law provides accurate error rate predictions. We further use it to show that in streaming applications periodic doping can yield higher rates than periodic full termination for the same error-correcting performance.

cs.IT↗
arXiv2021

Autoencoder-Based Unequal Error Protection Codes

We present a novel autoencoder-based approach for designing codes that provide unequal error protection (UEP) capabilities. The proposed design is based on a generalization of an autoencoder loss function that accommodates both message-wise and bit-wise UEP scenarios. In both scenarios, the generalized loss function can be adjusted using an associated weight vector to trade off error probabilities corresponding to different importance classes. For message-wise UEP, we compare the proposed autoencoder-based UEP codes with a union of random coset codes. For bit-wise UEP, the proposed codes are compared with UEP rateless spinal codes and the superposition of random Gaussian codes. In all cases, the autoencoder-based codes show superior performance while providing design simplicity and flexibility in trading off error protection among different importance classes.

cs.IT↗
arXiv2021

Dynamic Coded Caching in Wireless Networks Using Multi-Agent Reinforcement Learning

We consider distributed caching of content across several small base stations (SBSs) in a wireless network, where the content is encoded using a maximum distance separable code. Specifically, we apply soft time-to-live (STTL) cache management policies, where coded packets may be evicted from the caches at periodic times. We propose a reinforcement learning (RL) approach to find coded STTL policies minimizing the overall network load. We demonstrate that such caching policies achieve almost the same network load as policies obtained through optimization, where the latter assumes perfect knowledge of the distribution of times between file requests as well the distribution of the number of SBSs within communication range of a user placing a request. We also suggest a multi-agent RL (MARL) framework for the scenario of non-uniformly distributed requests in space. For such a scenario, we show that MARL caching policies achieve lower network load as compared to optimized caching policies assuming a uniform request placement. We also provide convincing evidence that synchronous updates offer a lower network load than asynchronous updates for spatially homogeneous renewal request processes due to the memory of the renewal processes.

cs.IT↗
arXiv2021

Low Complexity Joint Impairment Mitigation of I/Q Modulator and PA Using Neural Networks

Neural networks (NNs) for multiple hardware impairments mitigation of a realistic direct conversion transmitter are impractical due to high computational complexity. We propose two methods to reduce complexity without significant performance penalty. We first propose a novel attention residual learning NN, referred to as attention residual real-valued time-delay neural network (ARDEN), where trainable neuron-wise shortcut connections between the input and output layers allow to keep the attention always active. Furthermore, we implement a NN pruning algorithm that gradually removes connections corresponding to minimal weight magnitudes in each layer. Simulation and experimental results show that ARDEN with pruning achieves better performance for compensating frequency-dependent quadrature imbalance and power amplifier nonlinearity than other NN-based and Volterra-based models, while requiring less or similar complexity.

eess.SP↗
arXiv2021

The Capacity of Single-Server Weakly-Private Information Retrieval

A private information retrieval (PIR) protocol guarantees that a user can privately retrieve files stored in a database without revealing any information about the identity of the requested file. Existing information-theoretic PIR protocols ensure perfect privacy, i.e., zero information leakage to the servers storing the database, but at the cost of high download. In this work, we present weakly-private information retrieval (WPIR) schemes that trade off perfect privacy to improve the download cost when the database is stored on a single server. We study the tradeoff between the download cost and information leakage in terms of mutual information (MI) and maximal leakage (MaxL) privacy metrics. By relating the WPIR problem to rate-distortion theory, the download-leakage function, which is defined as the minimum required download cost of all single-server WPIR schemes for a given level of information leakage and a fixed file size, is introduced. By characterizing the download-leakage function for the MI and MaxL metrics, the capacity of single-server WPIR is fully described.

cs.IT↗
arXiv2020

Analysis and Design of Partially Information- and Partially Parity-Coupled Turbo Codes

In this paper, we study a class of spatially coupled turbo codes, namely partially information- and partially parity-coupled turbo codes. This class of codes enjoy several advantages such as flexible code rate adjustment by varying the coupling ratio and the encoding and decoding architectures of the underlying component codes can remain unchanged. For this work, we first provide the construction methods for partially coupled turbo codes with coupling memory $m$ and study the corresponding graph models. We then derive the density evolution equations for the corresponding ensembles on the binary erasure channel to precisely compute their iterative decoding thresholds. Rate-compatible designs and their decoding thresholds are also provided, where the coupling and puncturing ratios are jointly optimized to achieve the largest decoding threshold for a given target code rate. Our results show that for a wide range of code rates, the proposed codes attain close-to-capacity performance and the decoding performance improves with increasing the coupling memory. In particular, the proposed partially parity-coupled turbo codes have thresholds within 0.0002 of the BEC capacity for rates ranging from $1/3$ to $9/10$, yielding an attractive way for constructing rate-compatible capacity-approaching channel codes.

cs.IT↗
arXiv2020

Dynamic Coded Caching in Wireless Networks

We consider distributed and dynamic caching of coded content at small base stations (SBSs) in an area served by a macro base station (MBS). Specifically, content is encoded using a maximum distance separable code and cached according to a time-to-live (TTL) cache eviction policy, which allows coded packets to be removed from the caches at periodic times. Mobile users requesting a particular content download coded packets from SBSs within communication range. If additional packets are required to decode the file, these are downloaded from the MBS. We formulate an optimization problem that is efficiently solved numerically, providing TTL caching policies minimizing the overall network load. We demonstrate that distributed coded caching using TTL caching policies can offer significant reductions in terms of network load when request arrivals are bursty. We show how the distributed coded caching problem utilizing TTL caching policies can be analyzed as a specific single cache, convex optimization problem. Our problem encompasses static caching and the single cache as special cases. We prove that, interestingly, static caching is optimal under a Poisson request process, and that for a single cache the optimization problem has a surprisingly simple solution.

cs.IT↗
arXiv2020

Pruning and Quantizing Neural Belief Propagation Decoders

We consider near maximum-likelihood (ML) decoding of short linear block codes. In particular, we propose a novel decoding approach based on neural belief propagation (NBP) decoding recently introduced by Nachmani et al. in which we allow a different parity-check matrix in each iteration of the algorithm. The key idea is to consider NBP decoding over an overcomplete parity-check matrix and use the weights of NBP as a measure of the importance of the check nodes (CNs) to decoding. The unimportant CNs are then pruned. In contrast to NBP, which performs decoding on a given fixed parity-check matrix, the proposed pruning-based neural belief propagation (PB-NBP) typically results in a different parity-check matrix in each iteration. For a given complexity in terms of CN evaluations, we show that PB-NBP yields significant performance improvements with respect to NBP. We apply the proposed decoder to the decoding of a Reed-Muller code, a short low-density parity-check (LDPC) code, and a polar code. PB-NBP outperforms NBP decoding over an overcomplete parity-check matrix by 0.27-0.31 dB while reducing the number of required CN evaluations by up to 97%. For the LDPC code, PB-NBP outperforms conventional belief propagation with the same number of CN evaluations by 0.52 dB. We further extend the pruning concept to offset min-sum decoding and introduce a pruning-based neural offset min-sum (PB-NOMS) decoder, for which we jointly optimize the offsets and the quantization of the messages and offsets. We demonstrate performance 0.5 dB from ML decoding with 5-bit quantization for the Reed-Muller code.

cs.IT↗
arXiv2020

Learned Decimation for Neural Belief Propagation Decoders

We introduce a two-stage decimation process to improve the performance of neural belief propagation (NBP), recently introduced by Nachmani et al., for short low-density parity-check (LDPC) codes. In the first stage, we build a list by iterating between a conventional NBP decoder and guessing the least reliable bit. The second stage iterates between a conventional NBP decoder and learned decimation, where we use a neural network to decide the decimation value for each bit. For a (128,64) LDPC code, the proposed NBP with decimation outperforms NBP decoding by 0.75 dB and performs within 1 dB from maximum-likelihood decoding at a block error rate of $10^{-4}$.

cs.IT↗
arXiv2020

Concatenated Codes for Recovery From Multiple Reads of DNA Sequences

Decoding sequences that stem from multiple transmissions of a codeword over an insertion, deletion, and substitution channel is a critical component of efficient deoxyribonucleic acid (DNA) data storage systems. In this paper, we consider a concatenated coding scheme with an outer low-density parity-check code and either an inner convolutional code or a block code. We propose two new decoding algorithms for inference from multiple received sequences, both combining the inner code and channel to a joint hidden Markov model to infer symbolwise a posteriori probabilities (APPs). The first decoder computes the exact APPs by jointly decoding the received sequences, whereas the second decoder approximates the APPs by combining the results of separately decoded received sequences. Using the proposed algorithms, we evaluate the performance of decoding multiple received sequences by means of achievable information rates and Monte-Carlo simulations. We show significant performance gains compared to a single received sequence.

cs.IT↗
arXiv2020

Pruning Neural Belief Propagation Decoders

We consider near maximum-likelihood (ML) decoding of short linear block codes based on neural belief propagation (BP) decoding recently introduced by Nachmani et al.. While this method significantly outperforms conventional BP decoding, the underlying parity-check matrix may still limit the overall performance. In this paper, we introduce a method to tailor an overcomplete parity-check matrix to (neural) BP decoding using machine learning. We consider the weights in the Tanner graph as an indication of the importance of the connected check nodes (CNs) to decoding and use them to prune unimportant CNs. As the pruning is not tied over iterations, the final decoder uses a different parity-check matrix in each iteration. For Reed-Muller and short low-density parity-check codes, we achieve performance within 0.27 dB and 1.5 dB of the ML performance while reducing the complexity of the decoder.

cs.IT↗
arXiv2020

Private Edge Computing for Linear Inference Based on Secret Sharing

We consider an edge computing scenario where users want to perform a linear computation on local, private data and a network-wide, public matrix. Users offload computations to edge servers located at the edge of the network, but do not want the servers, or any other party with access to the wireless links, to gain any information about their data. We provide a scheme that guarantees information-theoretic user data privacy against an eavesdropper with access to a number of edge servers or their corresponding communication links. The novelty of the proposed scheme lies in the utilization of secret sharing and partial replication to provide privacy, mitigate the effect of straggling servers, and to allow for joint beamforming opportunities in the download phase, to minimize the overall latency, consisting of upload, computation, and download latencies.

cs.IT↗
arXiv2020

Residual Neural Networks for Digital Predistortion

Tracking the nonlinear behavior of an RF power amplifier (PA) is challenging. To tackle this problem, we build a connection between residual learning and the PA nonlinearity, and propose a novel residual neural network structure, referred to as the residual real-valued time-delay neural network (R2TDNN). Instead of learning the whole behavior of the PA, the R2TDNN focuses on learning its nonlinear behavior by adding identity shortcut connections between the input and output layer. In particular, we apply the R2TDNN to digital predistortion and measure experimental results on a real PA. Compared with neural networks recently proposed by Liu et al. and Wang et al., the R2TDNN achieves the best linearization performance in terms of normalized mean square error and adjacent channel power ratio with less or similar computational complexity. Furthermore, the R2TDNN exhibits significantly faster training speed and lower training error.

eess.SP↗