Scholars@Duke
Navid NaderiAlizadeh

Navid NaderiAlizadeh

Assistant Research Professor of Biostatistics & Bioinformatics
Biostatistics & Bioinformatics, Division of Integrative Genomics
2424 Erwin Road, 2721, Durham, NC 27705
2424 Erwin Road, 2721, Durham, NC 27705

Selected Publications

Black-box Optimization of CT Acquisition and Reconstruction Parameters: A Reinforcement Learning Approach.

Journal Article Proc SPIE Int Soc Opt Eng · February 2025 Protocol optimization is critical in Computed Tomography (CT) for achieving desired diagnostic image quality while minimizing radiation dose. Due to the inter-effect of influencing CT parameters, traditional optimization methods rely on the testing of exha ... Full text Link to item Cite

Learning State-Augmented Policies for Information Routing in Communication Networks

Journal Article IEEE Transactions on Signal Processing · January 1, 2025 This paper examines the problem of information routing in a large-scale communication network, which can be formulated as a constrained statistical learning problem having access to only local information. We delineate a novel State Augmentation (SA) strat ... Full text Cite

Aggregating residue-level protein language model embeddings with optimal transport.

Journal Article Bioinform Adv · 2025 MOTIVATION: Protein language models (PLMs) have emerged as powerful approaches for mapping protein sequences into embeddings suitable for various applications. As protein representation schemes, PLMs generate per-token (i.e. per-residue) representations, r ... Full text Open Access Link to item Cite

State-Augmented Opportunistic Routing in Wireless Communication Systems with Graph Neural Networks

Conference ICASSP IEEE International Conference on Acoustics Speech and Signal Processing Proceedings · January 1, 2025 In this study, we address the challenge of packet based information routing in large-scale wireless communication networks. We approach this scenario by framing the problem as a statistical learning problem, where each node in the network relies only on th ... Full text Cite

ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans

Conference Proceedings of Machine Learning Research · January 1, 2025 While self-attention has been instrumental in the success of Transformers, it can lead to overconcentration on a few tokens during training, resulting in suboptimal information flow. Enforcing doubly-stochastic constraints in attention matrices has been sh ... Cite

State-Augmented Information Routing In Communication Systems With Graph Neural Networks

Conference ICASSP IEEE International Conference on Acoustics Speech and Signal Processing Proceedings · January 1, 2024 We consider the problem of routing network packets in a large-scale communication system where the nodes have access to only local information. We formulate this problem as a constrained learning problem, which can be solved using a distributed optimizatio ... Full text Cite

Robust Stochastically-Descending Unrolled Networks

Journal Article IEEE Transactions on Signal Processing · January 1, 2024 Deep unrolling, or unfolding, is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. However, the convergence guarantees and generalizability of the unrolled networks are still o ... Full text Cite

Learning to Slice Wi-Fi Networks: A State-Augmented Primal-Dual Approach

Conference Proceedings IEEE Global Communications Conference Globecom · January 1, 2024 Network slicing is a key feature in 5G/NG cellular networks that creates customized slices for different service types with various quality-of-service (QoS) requirements, which can achieve service differentiation and guarantee service-level agreement (SLA) ... Full text Cite

Learning Resilient Radio Resource Management Policies With Graph Neural Networks

Journal Article IEEE Transactions on Signal Processing · January 1, 2023 We consider the problems of user selection and power control in wireless interference networks, comprising multiple access points (APs) communicating with a group of user equipment devices (UEs) over a shared wireless medium. To achieve a high aggregate ra ... Full text Cite

Guest Editorial: An End-to-End Machine Learning Perspective on Industrial IoT

Journal Article IEEE Internet of Things Magazine · March 1, 2022 Full text Cite

State-Augmented Learnable Algorithms for Resource Management in Wireless Networks

Journal Article IEEE Transactions on Signal Processing · January 1, 2022 We consider resource management problems in multi-user wireless networks, which can be cast as optimizing a network-wide utility function, subject to constraints on the long-term average performance of users across the network. We propose a state-augmented ... Full text Cite

ADAPTIVE WIRELESS POWER ALLOCATION WITH GRAPH NEURAL NETWORKS

Conference ICASSP IEEE International Conference on Acoustics Speech and Signal Processing Proceedings · January 1, 2022 We consider the problem of power control in wireless networks, consisting of multiple transmitter-receiver pairs communicating with each other over a single shared wireless medium. To achieve both a high total rate and a level of fairness across users, we ... Full text Cite

A Lagrangian Duality Approach to Active Learning

Conference Advances in Neural Information Processing Systems · January 1, 2022 We consider the pool-based active learning problem, where only a subset of the training data is labeled, and the goal is to query a batch of unlabeled samples to be labeled so as to maximally improve model performance. We formulate the problem using constr ... Cite

Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learning

Journal Article IEEE Transactions on Wireless Communications · June 1, 2021 We propose a mechanism for distributed resource management and interference mitigation in wireless networks using multi-agent deep reinforcement learning (RL). We equip each transmitter in the network with a deep RL agent that receives delayed observations ... Full text Cite

Contrastive self-supervised learning for wireless power control

Conference ICASSP IEEE International Conference on Acoustics Speech and Signal Processing Proceedings · January 1, 2021 We propose a new approach for power control in wireless networks using self-supervised learning. We partition a multi-layer perceptron that takes as input the channel matrix and outputs the power control decisions into a backbone and a head, and we show ho ... Full text Cite

Pooling by Sliced-Wasserstein Embedding

Conference Advances in Neural Information Processing Systems · January 1, 2021 Learning representations from sets has become increasingly important with many applications in point cloud processing, graph learning, image/video recognition, and object detection. We introduce a geometrically-interpretable and generic pooling mechanism f ... Cite

Optimizing the Configuration of Intelligent Reflecting Surfaces using Deep Learning

Conference 2021 IEEE Globecom Workshops GC Wkshps 2021 Proceedings · January 1, 2021 We consider a multi-user wireless network, where a single base station intends to communicate with multiple users by means of an intelligent reflecting surface (IRS), and we propose to optimize the IRS configuration using deep learning-based methodologies. ... Full text Cite

WASSERSTEIN EMBEDDING FOR GRAPH LEARNING

Conference Iclr 2021 9th International Conference on Learning Representations · January 1, 2021 We present Wasserstein Embedding for Graph Learning (WEGL), a novel and fast framework for embedding entire graphs in a vector space, in which various machine learning models are applicable for graph-level prediction tasks. We leverage new insights on defi ... Cite

Wireless Power Control via Counterfactual Optimization of Graph Neural Networks

Conference IEEE Workshop on Signal Processing Advances in Wireless Communications Spawc · May 1, 2020 We consider the problem of downlink power control in wireless networks, consisting of multiple transmitter-receiver pairs communicating with each other over a single shared wireless medium. To mitigate the interference among concurrent transmissions, we le ... Full text Cite

Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learning

Conference IEEE Workshop on Signal Processing Advances in Wireless Communications Spawc · May 1, 2020 We propose a mechanism for distributed radio resource management using multi-Agent deep reinforcement learning to mitigate the interference among concurrent transmissions in wireless networks. We equip each transmitter in the network with a deep RL agent, ... Full text Cite

Sar automatic target recognition with less labels

Conference Proceedings of SPIE the International Society for Optical Engineering · January 1, 2020 Synthetic-Aperture-Radar (SAR) is a commonly used modality in mission-critical remote-sensing applications, including battlefield intelligence, surveillance, and reconnaissance (ISR). Processing SAR sensory inputs with deep learning is challenging because ... Full text Cite

Learning to Code: Coded Caching via Deep Reinforcement Learning

Conference Conference Record Asilomar Conference on Signals Systems and Computers · November 1, 2019 We consider a system comprising a file library and a network with a server and multiple users equipped with cache memories. The system operates in two phases: a prefetching phase, where users load their caches with parts of contents from the library, and a ... Full text Cite

Energy-Aware Multi-Server Mobile Edge Computing: A Deep Reinforcement Learning Approach

Conference Conference Record Asilomar Conference on Signals Systems and Computers · November 1, 2019 We investigate the problem of computation offloading in a mobile edge computing architecture, where multiple energy-constrained users compete to offload their computational tasks to multiple servers through a shared wireless medium. We propose a multi-agen ... Full text Cite

Monitoring Under-Modeled Rare Events for URLLC

Conference IEEE Workshop on Signal Processing Advances in Wireless Communications Spawc · July 1, 2019 Immersive and interactive applications that demand ultra-reliable low-latency communication (URLLC) are gaining traction, particularly in the latest 3GPP standards on 5G. The main focus in standards and research has primarily been on protocols based on tec ... Full text Cite

Cache-Aided Interference Management in Wireless Cellular Networks

Journal Article IEEE Transactions on Communications · May 1, 2019 We consider the problem of interference management in wireless cellular networks with caches at both base stations and receivers, and we characterize the degrees of freedom (DoFs) per cell to within an additive gap of (1/3) and a multiplicative gap of 2 fo ... Full text Cite

Deep CNN for Wideband Mmwave Massive Mimo Channel Estimation Using Frequency Correlation

Conference ICASSP IEEE International Conference on Acoustics Speech and Signal Processing Proceedings · May 1, 2019 For millimeter wave (mmWave) systems with large-scale arrays, hybrid processing structure is usually used at both transmitters and receivers to reduce the complexity and cost, which poses a very challenging issue in channel estimation, especially at the lo ... Full text Cite

A power efficient fully digital beamforming architecture for mmwave communications

Conference IEEE Vehicular Technology Conference · April 1, 2019 A typical wireless transceiver includes a radio frequency integrated circuit (RFIC) and a baseband modem (BBIC) which are connected through an input/output (I/O) interface. The wide-bandwidth and high-rate millimeter wave (mmWave) systems put a heavy burde ... Full text Cite

Deep CNN-Based Channel Estimation for mmWave Massive MIMO Systems

Journal Article IEEE Journal on Selected Topics in Signal Processing · January 1, 2019 For millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, hybrid processing architecture is usually used to reduce the complexity and cost, which poses a very challenging issue in channel estimation. In this paper, deep convolutio ... Full text Cite

Feedback-Based Interference Management in Ultra-Dense Networks via Parallel Dynamic Cell Selection and Link Scheduling

Conference IEEE International Conference on Communications · July 27, 2018 We present a method for parallel dynamic cell selection and link scheduling in order to simultaneously activate a subset of non- interfering transmitter-receiver links to manage the interference in an ultra-dense network setting. We show how we can utilize ... Full text Cite

Topological Interference Management with Reconfigurable Antennas

Conference IEEE Transactions on Communications · November 1, 2017 We study the symmetric degrees-of-freedom (DoF) of partially connected interference networks under linear coding strategies without channel state information at the transmitters beyond topology. We assume that the receivers are equipped with reconfigurable ... Full text Cite

Fundamental Limits of Non-Coherent Interference Alignment via Matroid Theory

Journal Article IEEE Transactions on Information Theory · October 1, 2017 We consider the problem of non-coherent interference alignment, in which the goal is to align the signals of multiple interfering transmitters at a single receiver where the transmitters are not aware of the channel state information. We cast this problem ... Full text Cite

On the optimality of separation between caching and delivery in general cache networks

Conference IEEE International Symposium on Information Theory Proceedings · August 9, 2017 We consider a system, containing a library of multiple files and a general memoryless communication network through which a server is connected to multiple users, each equipped with a local isolated cache of certain size that can be used to store part of t ... Full text Cite

Cache-aided interference management in wireless cellular networks

Conference IEEE International Conference on Communications · July 28, 2017 We consider the problem of interference management in wireless cellular networks with caches at both base stations and receivers and we characterize the degrees-of-freedom (DoF) per cell to within an additive gap of 1 and a multiplicative gap of 2 for all ... Full text Cite

Ultra-dense networks in 5g: Interference management via non-orthogonal multiple access and treating interference as noise

Conference IEEE Vehicular Technology Conference · July 2, 2017 We propose a method for interference mitigation in an ultra-dense wireless network scenario in 5G, where a group of transmit points (TPs) intend to serve multiple user equipments (UEs) using the same wireless resource. The proposed UE scheduling subroutine ... Full text Cite

Fundamental Limits of Cache-Aided Interference Management

Journal Article IEEE Transactions on Information Theory · May 1, 2017 We consider a system, comprising a library of N files (e.g., movies) and a wireless network with a KT transmitters, each equipped with a local cache of size of MT files and a KR receivers, each equipped with a local cache o ... Full text Cite

Fundamental limits of cache-aided interference management

Conference IEEE International Symposium on Information Theory Proceedings · August 10, 2016 We consider a system, comprising a library of files (e.g., movies) and a wireless network with an arbitrary number of transmitters and receivers, where each node is equipped with a local cache memory. The system operates in two phases, the prefetching phas ... Full text Cite

Topological interference management with reconfigurable antennas

Conference IEEE International Symposium on Information Theory Proceedings · August 10, 2016 We study the symmetric degrees-of-freedom (DoF) of partially connected interference networks under linear coding strategies without channel state information at the transmitters beyond topology. We assume that the receivers are equipped with reconfigurable ... Full text Cite

When does an ensemble of matrices with randomly scaled rows lose rank?

Conference IEEE International Symposium on Information Theory Proceedings · September 28, 2015 We consider the problem of determining rank loss conditions for a concatenation of full-rank matrices, such that each row of the composing matrices is scaled by a random coefficient. This problem has applications in wireless interference management and rec ... Full text Cite

Topological interference management with just retransmission: What are the 'Best' topologies?

Conference IEEE International Conference on Communications · September 9, 2015 We study the problem of interference management in fast fading wireless networks, in which the transmitters are only aware of network topology. We consider a class of retransmission-based schemes, where transmitters in the network are only allowed to resen ... Full text Cite

On the Optimality of Treating Interference as Noise

Journal Article IEEE Transactions on Information Theory · April 1, 2015 It is shown that in the K-user interference channel, if for each user the desired signal strength is no less than the sum of the strengths of the strongest interference from this user and the strongest interference to this user (all values in decibel scale ... Full text Cite

Interference networks with no CSIT: Impact of topology

Journal Article IEEE Transactions on Information Theory · February 1, 2015 We consider partially connected K-user interference networks, where the transmitters have no knowledge about the channel gain values, but they are aware of network topology. We introduce several linear algebraic and graph theoretic concepts to derive new t ... Full text Cite

How to utilize caching to improve spectral efficiency in device-to-device wireless networks

Conference 2014 52nd Annual Allerton Conference on Communication Control and Computing Allerton 2014 · January 30, 2014 In this paper, we study the impact of caching on a recently-proposed spectrum sharing mechanism for device-to-device networks, ITLinQ, which schedules communication based on information-theoretic optimality principles. We provide a lower bound on the spect ... Full text Cite

ITLinQ: A new approach for spectrum sharing in device-to-device communication systems

Conference IEEE International Symposium on Information Theory Proceedings · January 1, 2014 We consider the problem of spectrum sharing in device-to-device communication systems. Based on the recently-found condition for the optimality of treating interference as noise, we introduce the new notion of information-theoretic independent set (ITIS) w ... Full text Cite

ITLinQ: A new approach for spectrum sharing

Conference 2014 IEEE International Symposium on Dynamic Spectrum Access Networks Dyspan 2014 · January 1, 2014 We consider the problem of spectrum sharing in wireless communication networks composed of multiple source-destination pairs. We define a novel concept of information-theoretic independent sets (in short, ITIS) which indicates the sets of source-destinatio ... Full text Cite

ITLinQ: A new approach for spectrum sharing in device-to-device communication systems

Journal Article IEEE Journal on Selected Areas in Communications · January 1, 2014 We consider the problem of spectrum sharing in device-to-device communication systems. Inspired by the recent optimality condition for treating interference as noise, we define a new concept of information-theoretic independent sets (ITISs), which indicate ... Full text Cite

Impact of topology on interference networks with no CSIT

Conference IEEE International Symposium on Information Theory Proceedings · December 19, 2013 We study the symmetric degrees-of-freedom (DoF) of partially connected K-user interference networks in which the transmitters are unaware of the actual channel gain values. Several linear algebraic and graph theoretic concepts are introduced to derive new ... Full text Cite

On the optimality of treating interference as noise

Conference 2013 51st Annual Allerton Conference on Communication Control and Computing Allerton 2013 · January 1, 2013 It is shown that in the K-user interference channel, if for each user the desired signal strength is no less than the sum of the strengths of the strongest interference from this user and the strongest interference to this user (all values in dB scale), th ... Full text Cite