Elza Erkip

Federico Boccardi, Hossein Shokri-Ghadikolaei, Gabor Fodor et al.

Motivated by the intrinsic characteristics of mmWave technologies, we discuss the possibility of an authorization regime that allows spectrum sharing between multiple operators, also referred to as spectrum pooling. In particular, considering user rate as the performance measure, we assess the benefit of coordination among the networks of different operators, study the impact of beamforming both at the base stations and at the user terminals, and analyze the pooling performance at different frequency carriers. We also discuss the enabling spectrum mechanisms, architectures, and protocols required to make spectrum pooling work in real networks. Our initial results show that, from a technical perspective, spectrum pooling at mmWave has the potential for a more efficient spectrum use than a traditional exclusive spectrum allocation to a single operator. However, further studies are needed in order to reach a thorough understanding of this matter, and we hope that this paper will help stimulate further research in this area.

Zhongzheng Yuan, Samyak Rawlekar, Siddharth Garg et al.

Recent advances in computer vision has led to a growth of interest in deploying visual analytics model on mobile devices. However, most mobile devices have limited computing power, which prohibits them from running large scale visual analytics neural networks. An emerging approach to solve this problem is to offload the computation of these neural networks to computing resources at an edge server. Efficient computation offloading requires optimizing the trade-off between multiple objectives including compressed data rate, analytics performance, and computation speed. In this work, we consider a "split computation" system to offload a part of the computation of the YOLO object detection model. We propose a learnable feature compression approach to compress the intermediate YOLO features with light-weight computation. We train the feature compression and decompression module together with the YOLO model to optimize the object detection accuracy under a rate constraint. Compared to baseline methods that apply either standard image compression or learned image compression at the mobile and perform image decompression and YOLO at the edge, the proposed system achieves higher detection accuracy at the low to medium rate range. Furthermore, the proposed system requires substantially lower computation time on the mobile device with CPU only.

Selim F. Yilmaz, Ezgi Ozyilkan, Deniz Gunduz et al.

We consider low-latency image transmission over a noisy wireless channel when correlated side information is present only at the receiver side (the Wyner-Ziv scenario). In particular, we are interested in developing practical schemes using a data-driven joint source-channel coding (JSCC) approach, which has been previously shown to outperform conventional separation-based approaches in the practical finite blocklength regimes, and to provide graceful degradation with channel quality. We propose a novel neural network architecture that incorporates the decoder-only side information at multiple stages at the receiver side. Our results demonstrate that the proposed method succeeds in integrating the side information, yielding improved performance at all channel conditions in terms of the various quality measures considered here, especially at low channel signal-to-noise ratios (SNRs) and small bandwidth ratios (BRs). We have made the source code of the proposed method public to enable further research, and the reproducibility of the results.

Fabrizio Carpi, Sivarama Venkatesan, Jinfeng Du et al.

Downlink massive multiple-input multiple-output (MIMO) precoding algorithms in frequency division duplexing (FDD) systems rely on accurate channel state information (CSI) feedback from users. In this paper, we analyze the tradeoff between the CSI feedback overhead and the performance achieved by the users in systems in terms of achievable rate. The final goal of the proposed system is to determine the beamforming information (i.e., precoding) from channel realizations. We employ a deep learning-based approach to design the end-to-end precoding-oriented feedback architecture, that includes learned pilots, users' compressors, and base station processing. We propose a loss function that maximizes the sum of achievable rates with minimal feedback overhead. Simulation results show that our approach outperforms previous precoding-oriented methods, and provides more efficient solutions with respect to conventional methods that separate the CSI compression blocks from the precoding processing.

Ozan Aygün, Vincenzo Norman Vitale, Antonia M. Tulino et al.

Next-generation networks aim to provide performance guarantees to real-time interactive services that require timely and cost-efficient packet delivery. In this context, the goal is to reliably deliver packets with strict deadlines imposed by the application while minimizing overall resource allocation cost. A large body of work has leveraged stochastic optimization techniques to design efficient dynamic routing and scheduling solutions under average delay constraints; however, these methods fall short when faced with strict per-packet delay requirements. We formulate the minimum-cost delay-constrained network control problem as a constrained Markov decision process and utilize constrained deep reinforcement learning (CDRL) techniques to effectively minimize total resource allocation cost while maintaining timely throughput above a target reliability level. Results indicate that the proposed CDRL-based solution can ensure timely packet delivery even when existing baselines fall short, and it achieves lower cost compared to other throughput-maximizing methods.

Fabrizio Carpi, Soheil Rostami, Joonyoung Cho et al.

High peak-to-average power ratio (PAPR) is one of the main factors limiting cell coverage for cellular systems, especially in the uplink direction. Discrete Fourier transform spread orthogonal frequency-domain multiplexing (DFT-s-OFDM) with spectrally-extended frequency-domain spectrum shaping (FDSS) is one of the efficient techniques deployed to lower the PAPR of the uplink waveforms. In this work, we propose a machine learning-based framework to determine the FDSS filter, optimizing a tradeoff between the symbol error rate (SER), the PAPR, and the spectral flatness requirements. Our end-to-end optimization framework considers multiple important design constraints, including the Nyquist zero-ISI (inter-symbol interference) condition. The numerical results show that learned FDSS filters lower the PAPR compared to conventional baselines, with minimal SER degradation. Tuning the parameters of the optimization also helps us understand the fundamental limitations and characteristics of the FDSS filters for PAPR reduction.

Mingsheng Yin, Akshaj Veldanda, Amee Trivedi et al.

The millimeter wave (mmWave) bands have attracted considerable attention for high precision localization applications due to the ability to capture high angular and temporal resolution measurements. This paper explores mmWave-based positioning for a target localization problem where a fixed target broadcasts mmWave signals and a mobile robotic agent attempts to capture the signals to locate and navigate to the target. A three-stage procedure is proposed: First, the mobile agent uses tensor decomposition methods to detect the multipath channel components and estimate their parameters. Second, a machine-learning trained classifier is then used to predict the link state, meaning if the strongest path is line-of-sight (LOS) or non-LOS (NLOS). For the NLOS case, the link state predictor also determines if the strongest path arrived via one or more reflections. Third, based on the link state, the agent either follows the estimated angles or uses computer vision or other sensor to explore and map the environment. The method is demonstrated on a large dataset of indoor environments supplemented with ray tracing to simulate the wireless propagation. The path estimation and link state classification are also integrated into a state-of-the-art neural simultaneous localization and mapping (SLAM) module to augment camera and LIDAR-based navigation. It is shown that the link state classifier can successfully generalize to completely new environments outside the training set. In addition, the neural-SLAM module with the wireless path estimation and link state classifier provides rapid navigation to the target, close to a baseline that knows the target location.

Abbas Khalili, Sundeep Rangan, Elza Erkip

Communication in high frequencies such as millimeter wave and terahertz suffer from high path-loss and intense shadowing which necessitates beamforming for reliable data transmission. On the other hand, at high frequencies the channels are sparse and consist of few spatial clusters. Therefore, beam alignment (BA) strategies are used to find the direction of these channel clusters and adjust the width of the beam used for data transmission. In this work, a single-user uplink scenario where the channel has one dominant cluster is considered. It is assumed that the user transmits a set of BA packets over a fixed duration. Meanwhile, the base-station (BS) uses different probing beams to scan different angular regions. Since the BS measurements are noisy, it is not possible to find a narrow beam that includes the angle of arrival (AoA) of the user with probability one. Therefore, the BS allocates a narrow beam to the user which includes the AoA of the user with a predetermined error probability while minimizing the expected beamwidth of the allocated beam. Due to intractability of this noisy BA problem, here this problem is posed as an end-to-end optimization of a deep neural network (DNN) and effects of different loss functions are discussed and investigated. It is observed that the proposed DNN based BA, at high SNRs, achieves a performance close to that of the optimal BA when there is no-noise and for all SNRs, outperforms state-of-the-art.

Vahid Jamali, Antonia Tulino, Jaime Llorca et al.

Semi-supervised classification, one of the most prominent fields in machine learning, studies how to combine the statistical knowledge of the often abundant unlabeled data with the often limited labeled data in order to maximize overall classification accuracy. In this context, the process of actively choosing the data to be labeled is referred to as active learning. In this paper, we initiate the non-asymptotic analysis of the optimal policy for semi-supervised classification with actively obtained labeled data. Considering a general Bayesian classification model, we provide the first characterization of the jointly optimal active learning and semi-supervised classification policy, in terms of the cost-performance tradeoff driven by the label query budget (number of data items to be labeled) and overall classification accuracy. Leveraging recent results on the Rényi Entropy, we derive tight information-theoretic bounds on such active learning cost-performance tradeoff.

Farhad Shirani, Siddharth Garg, Elza Erkip

In this paper, a new mathematical formulation for the problem of de-anonymizing social network users by actively querying their membership in social network groups is introduced. In this formulation, the attacker has access to a noisy observation of the group membership of each user in the social network. When an unidentified victim visits a malicious website, the attacker uses browser history sniffing to make queries regarding the victim's social media activity. Particularly, it can make polar queries regarding the victim's group memberships and the victim's identity. The attacker receives noisy responses to her queries. The goal is to de-anonymize the victim with the minimum number of queries. Starting with a rigorous mathematical model for this active de-anonymization problem, an upper bound on the attacker's expected query cost is derived, and new attack algorithms are proposed which achieve this bound. These algorithms vary in computational cost and performance. The results suggest that prior heuristic approaches to this problem provide sub-optimal solutions.

Mustafa A. Kocak, David Ramirez, Elza Erkip et al.

SafePredict is a novel meta-algorithm that works with any base prediction algorithm for online data to guarantee an arbitrarily chosen correctness rate, $1-ε$, by allowing refusals. Allowing refusals means that the meta-algorithm may refuse to emit a prediction produced by the base algorithm on occasion so that the error rate on non-refused predictions does not exceed $ε$. The SafePredict error bound does not rely on any assumptions on the data distribution or the base predictor. When the base predictor happens not to exceed the target error rate $ε$, SafePredict refuses only a finite number of times. When the error rate of the base predictor changes through time SafePredict makes use of a weight-shifting heuristic that adapts to these changes without knowing when the changes occur yet still maintains the correctness guarantee. Empirical results show that (i) SafePredict compares favorably with state-of-the art confidence based refusal mechanisms which fail to offer robust error guarantees; and (ii) combining SafePredict with such refusal mechanisms can in many cases further reduce the number of refusals. Our software (currently in Python) is included in the supplementary material.

Zhili Guo, Yao Wang, Elza Erkip et al.

In this paper, a cooperative multicast scheme that uses Randomized Distributed Space Time Codes (R-DSTC), along with packet level Forward Error Correction (FEC), is studied. Instead of sending source packets and/or parity packets through two hops using R-DSTC as proposed in our prior work, the new scheme delivers both source packets and parity packets using only one hop. After the source station (access point, AP) first sends all the source packets, the AP as well as all nodes that have received all source packets together send the parity packets using R-DSTC. As more parity packets are transmitted, more nodes can recover all source packets and join the parity packet transmission. The process continues until all nodes acknowledge the receipt of enough packets for recovering the source packets. For each given node distribution, the optimum transmission rates for source and parity packets are determined such that the video rate that can be sustained at all nodes is maximized. This new scheme can support significantly higher video rates, and correspondingly higher PSNR of decoded video, than the prior approaches. Three suboptimal approaches, which do not require full information about user distribution or the feedback, and hence are more feasible in practice are also presented. The proposed suboptimal scheme with only the node count information and without feedback still outperforms our prior approach that assumes full channel information and no feedback.