no code implementations • 17 Apr 2024 • Jiayi Huang, Sangwoo Park, Osvaldo Simeone
This paper proposes an extension of variational inference (VI)-based Bayesian learning that integrates calibration regularization for improved ID performance, confidence minimization for OOD detection, and selective calibration to ensure a synergistic use of calibration regularization and confidence minimization.
no code implementations • 9 Apr 2024 • Zihang Song, Osvaldo Simeone, Bipin Rajendran
In-context learning (ICL), a property demonstrated by transformer-based sequence models, refers to the automatic inference of an input-output mapping based on examples of the mapping provided as context.
2 code implementations • 8 Apr 2024 • Matteo Zecchin, Kai Yu, Osvaldo Simeone
In this work, we demonstrate that ICL can be also used to tackle the problem of multi-user equalization in cell-free MIMO systems with limited fronthaul capacity.
no code implementations • 2 Apr 2024 • Yuzhen Ke, Zoran Utkovski, Mehdi Heshmati, Osvaldo Simeone, Johannes Dommel, Slawomir Stanczak
An important use case of next-generation wireless systems is device-edge co-inference, where a semantic task is partitioned between a device and an edge server.
no code implementations • 2 Apr 2024 • Jiechen Chen, Sangwoo Park, Petar Popovski, H. Vincent Poor, Osvaldo Simeone
This work proposes a novel architecture that integrates a wake-up radio mechanism within a split computing system consisting of remote, wirelessly connected, NPUs.
no code implementations • 14 Mar 2024 • Yunchuan Zhang, Sangwoo Park, Osvaldo Simeone
In many applications, ranging from logistics to engineering, a designer is faced with a sequence of optimization tasks for which the objectives are in the form of black-box functions that are costly to evaluate.
no code implementations • 16 Feb 2024 • Meiyi Zhu, Caili Guo, Chunyan Feng, Osvaldo Simeone
We derive bounds on the advantage of an MIA adversary with the aim of offering insights into the impact of uncertainty and calibration on the effectiveness of MIAs.
no code implementations • 14 Feb 2024 • Zihang Song, Prabodh Katti, Osvaldo Simeone, Bipin Rajendran
Spiking Neural Networks (SNNs) have been recently integrated into Transformer architectures due to their potential to reduce computational demands and to improve power efficiency.
no code implementations • 13 Feb 2024 • Eslam Eldeeb, Houssem Sifaou, Osvaldo Simeone, Mohammad Shehab, Hirley Alves
Digital twin (DT) platforms are increasingly regarded as a promising technology for controlling, optimizing, and monitoring complex engineering systems such as next-generation wireless networks.
no code implementations • 31 Jan 2024 • Petros Georgiou, Sharu Theresa Jose, Osvaldo Simeone
Specifically, a quantum adversary maximizes the classifier's loss by transforming an input state $\rho(x)$ into a state $\lambda$ that is $\epsilon$-close to the original state $\rho(x)$ in $p$-Schatten distance.
no code implementations • 22 Jan 2024 • Matteo Zecchin, Sangwoo Park, Osvaldo Simeone, Fredrik Hellström
A popular technique to achieve this goal is conformal prediction (CP), which transforms an arbitrary base predictor into a set predictor with coverage guarantees.
no code implementations • 22 Jan 2024 • Kfir M. Cohen, Sangwoo Park, Osvaldo Simeone, Shlomo Shamai
CV-CRC is proved to offer theoretical guarantees on the average risk of the set predictor.
no code implementations • 15 Jan 2024 • Mingzhao Guo, Dongzhu Liu, Osvaldo Simeone, Dingzhu Wen
This paper presents a novel approach to enhance the communication efficiency of federated learning (FL) in multiple input and multiple output (MIMO) wireless systems.
no code implementations • 12 Jan 2024 • Eva Lagunas, Flor Ortiz, Geoffrey Eappen, Saed Daoud, Wallace Alves Martins, Jorge Querol, Symeon Chatzinotas, Nicolas Skatchkovsky, Bipin Rajendran, Osvaldo Simeone
Spiking neural networks (SNNs) implemented on neuromorphic processors (NPs) can enhance the energy efficiency of deployments of artificial intelligence (AI) for specific workloads.
1 code implementation • 19 Dec 2023 • Clement Ruah, Osvaldo Simeone, Jakob Hoydis, Bashir Al-Hashimi
This paper proposes a novel channel response-based scheme that, unlike the state of the art, estimates and compensates for the phase errors in the RT-generated channel responses.
no code implementations • 14 Nov 2023 • Victor Croisfelt, Shashi Raj Pandey, Osvaldo Simeone, Petar Popovski
Conventional retransmission (ARQ) protocols are designed with the goal of ensuring the correct reception of all the individual transmitter's packets at the receiver.
1 code implementation • 10 Nov 2023 • Matteo Zecchin, Kai Yu, Osvaldo Simeone
In ICL, a decision on a new input is made via a direct mapping of the input and of a few examples from the given task, serving as the task's context, to the output variable.
no code implementations • 25 Oct 2023 • Jiechen Chen, Sangwoo Park, Osvaldo Simeone
Spiking neural networks (SNNs) are recurrent models that can leverage sparsity in input time series to efficiently carry out tasks such as classification.
no code implementations • 25 Oct 2023 • Haifeng Wen, Hong Xing, Osvaldo Simeone
Addressing the communication bottleneck inherent in federated learning (FL), over-the-air FL (AirFL) has emerged as a promising solution, which is, however, hampered by deep fading conditions.
no code implementations • 16 Oct 2023 • Matteo Zecchin, Sangwoo Park, Osvaldo Simeone
This property is leveraged to devise a novel model predictive control (MPC) framework that addresses open-loop and closed-loop control problems under general average constraints on the quality or safety of the control policy.
no code implementations • 27 Sep 2023 • Bipin Rajendran, Osvaldo Simeone, Bashir M. Al-Hashimi
Artificial intelligence (AI) algorithms based on neural networks have been designed for decades with the goal of maximising some measure of accuracy.
no code implementations • 20 Sep 2023 • Leonardo Banchi, Jason Luke Pereira, Sharu Theresa Jose, Osvaldo Simeone
Recent years have seen significant activity on the problem of using data for the purpose of learning properties of quantum systems or of processing classical or quantum data via quantum computing.
no code implementations • 22 Aug 2023 • Flor Ortiz, Nicolas Skatchkovsky, Eva Lagunas, Wallace A. Martins, Geoffrey Eappen, Saed Daoud, Osvaldo Simeone, Bipin Rajendran, Symeon Chatzinotas
The latest satellite communication (SatCom) missions are characterized by a fully reconfigurable on-board software-defined payload, capable of adapting radio resources to the temporal and spatial variations of the system traffic.
no code implementations • 8 Aug 2023 • Meiyi Zhu, Matteo Zecchin, Sangwoo Park, Caili Guo, Chunyan Feng, Osvaldo Simeone
Recent work has introduced federated conformal prediction (CP), which leverages devices-to-server communication to improve the reliability of the server's decision.
no code implementations • 30 Jun 2023 • Yunchuan Zhang, Sangwoo Park, Osvaldo Simeone
Focusing on methods based on Bayesian optimization (BO), prior art has introduced an optimization scheme -- referred to as SAFEOPT -- that is guaranteed not to select any unsafe solution with a controllable probability over feedback noise as long as strict assumptions on the safety constraint function are met.
no code implementations • 18 May 2023 • Jiechen Chen, Sangwoo Park, Osvaldo Simeone
Spiking neural networks (SNNs) process time-series data via internal event-driven neural dynamics whose energy consumption depends on the number of spikes exchanged between neurons over the course of the input presentation.
no code implementations • 18 May 2023 • Haifeng Wen, Hong Xing, Osvaldo Simeone
For additive white Gaussian noise (AWGN) channels with instantaneous per-device power constraints, prior work has demonstrated the optimality of a power control mechanism based on norm clipping.
no code implementations • 12 May 2023 • Jiayi Huang, Sangwoo Park, Osvaldo Simeone
Deep learning models, including modern systems like large language models, are well known to offer unreliable estimates of the uncertainty of their decisions.
no code implementations • 7 May 2023 • Boning Zhang, Dongzhu Liu, Osvaldo Simeone, Guangxu Zhu
The recent development of scalable Bayesian inference methods has renewed interest in the adoption of Bayesian learning as an alternative to conventional frequentist learning that offers improved model calibration via uncertainty quantification.
1 code implementation • 6 Apr 2023 • Sangwoo Park, Osvaldo Simeone
In this work, we aim at augmenting the decisions output by quantum models with "error bars" that provide finite-sample coverage guarantees.
1 code implementation • 15 Feb 2023 • Kfir M. Cohen, Sangwoo Park, Osvaldo Simeone, Petar Popovski, Shlomo Shamai
The dynamic scheduling of ultra-reliable and low-latency traffic (URLLC) in the uplink can significantly enhance the efficiency of coexisting services, such as enhanced mobile broadband (eMBB) devices, by only allocating resources when necessary.
no code implementations • 2 Feb 2023 • Prabodh Katti, Nicolas Skatchkovsky, Osvaldo Simeone, Bipin Rajendran, Bashir M. Al-Hashimi
Bayesian Neural Networks (BNNs) can overcome the problem of overconfidence that plagues traditional frequentist deep neural networks, and are hence considered to be a key enabler for reliable AI systems.
no code implementations • 19 Jan 2023 • Ivana Nikoloska, Osvaldo Simeone, Leonardo Banchi, Petar Veličković
Adaptive gating plays a key role in temporal data processing via classical recurrent neural networks (RNN), as it facilitates retention of past information necessary to predict the future, providing a mechanism that preserves invariance to time warping transformations.
no code implementations • 16 Jan 2023 • Yunchuan Zhang, Osvaldo Simeone, Sharu Theresa Jose, Lorenzo Maggi, Alvaro Valcarce
Optimal resource allocation in modern communication networks calls for the optimization of objective functions that are only accessible via costly separate evaluations for each candidate solution.
no code implementations • 19 Dec 2022 • Meiyi Zhu, Chunyan Feng, Caili Guo, Nan Jiang, Osvaldo Simeone
Type-based multiple access (TBMA) is a semantics-aware multiple access protocol for remote inference.
no code implementations • 15 Dec 2022 • Kfir M. Cohen, Sangwoo Park, Osvaldo Simeone, Shlomo Shamai
This paper investigates the application of conformal prediction as a general framework to obtain AI models that produce decisions with formal calibration guarantees.
no code implementations • 9 Dec 2022 • Hari Hara Suthan Chittoor, Osvaldo Simeone, Leonardo Banchi, Stefano Pirandola
Simulating quantum channels is a fundamental primitive in quantum computing, since quantum channels define general (trace-preserving) quantum operations.
no code implementations • 2 Dec 2022 • Clement Ruah, Osvaldo Simeone, Bashir Al-Hashimi
A key challenge in the deployment of DT systems is to ensure that virtual control optimization, monitoring, and analysis at the DT are safe and reliable, avoiding incorrect decisions caused by "model exploitation".
no code implementations • 19 Oct 2022 • Luca Barbieri, Osvaldo Simeone, Monica Nicoli
Bayesian Federated Learning (FL) offers a principled framework to account for the uncertainty caused by limitations in the data available at the nodes implementing collaborative training.
no code implementations • 11 Oct 2022 • WenBo Du, Tao Tan, Haijun Zhang, Xianbin Cao, Gang Yan, Osvaldo Simeone
If the data timings and ACK timings of two nodes -- say node 1 and node 2, respectively -- are causally related, this may be taken as evidence that node 1 is communicating to node 2 (which sends back ACK packets to node 1).
1 code implementation • 11 Oct 2022 • Clement Ruah, Osvaldo Simeone, Bashir Al-Hashimi
Commonly adopted in the manufacturing and aerospace sectors, digital twin (DT) platforms are increasingly seen as a promising paradigm to control and monitor software-based, "open", communication systems, which play the role of the physical twin (PT).
no code implementations • 10 Oct 2022 • Kfir M. Cohen, Sangwoo Park, Osvaldo Simeone, Shlomo Shamai
We propose to leverage the conformal prediction framework to obtain data-driven set predictions whose calibration properties hold irrespective of the data distribution.
1 code implementation • 6 Oct 2022 • Sangwoo Park, Kfir M. Cohen, Osvaldo Simeone
Conventional frequentist learning is known to yield poorly calibrated models that fail to reliably quantify the uncertainty of their decisions.
no code implementations • 3 Oct 2022 • Lisha Chen, Sharu Theresa Jose, Ivana Nikoloska, Sangwoo Park, Tianyi Chen, Osvaldo Simeone
This review monograph provides an introduction to meta-learning by covering principles, algorithms, theory, and engineering applications.
no code implementations • 24 Sep 2022 • Jiechen Chen, Nicolas Skatchkovsky, Osvaldo Simeone
Neuromorphic computing is an emerging technology that support event-driven data processing for applications requiring efficient online inference and/or control.
no code implementations • 23 Sep 2022 • Sharu Theresa Jose, Osvaldo Simeone
It is shown that quantum gate noise induces a non-zero error-floor on the convergence error of SGD (evaluated with respect to a reference noiseless PQC), which depends on the number of noisy gates, the strength of the noise, as well as the eigenspectrum of the observable being measured and minimized.
no code implementations • 14 Sep 2022 • Jinu Gong, Osvaldo Simeone, Joonhyuk Kang
Conventional frequentist FL schemes are known to yield overconfident decisions.
1 code implementation • 29 Aug 2022 • Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone
In this paper, we take steps towards the design of neuromorphic systems that are capable of adaptation to changing learning tasks, while producing well-calibrated uncertainty quantification estimates.
1 code implementation • 22 Jul 2022 • Hari Hara Suthan Chittoor, Osvaldo Simeone
Distributed quantum information processing protocols such as quantum entanglement distillation and quantum state discrimination rely on local operations and classical communications (LOCC).
no code implementations • 13 Jul 2022 • Riccardo Marini, Sangwoo Park, Osvaldo Simeone, Chiara Buratti
Unmanned aerial base stations (UABSs) can be deployed in vehicular wireless networks to support applications such as extended sensing via vehicle-to-everything (V2X) services.
no code implementations • 1 Jul 2022 • Matteo Zecchin, Sangwoo Park, Osvaldo Simeone, Marios Kountouris, David Gesbert
In this context, we explore the application of the framework of robust Bayesian learning.
no code implementations • 16 Jun 2022 • Nidhi Simmons, Samuel B. Ferreira Gomes, Michel Daoud Yacoub, Osvaldo Simeone, Simon L Cotton, David E. Simmons
It is observed that GRUs and LSTMs present equivalent performance, and both are superior when compared to CNNs, FFNs and linear regression.
no code implementations • 13 Jun 2022 • Jiechen Chen, Nicolas Skatchkovsky, Osvaldo Simeone
In order to enable adaptation of the receiver to the fading channel conditions, we introduce a hypernetwork to control the weights of the decoding SNN using pilots.
1 code implementation • 17 May 2022 • Hari Hara Suthan Chittoor, Osvaldo Simeone
Therefore, an important primitive for quantum networking is entanglement distillation, whose goal is to enhance the fidelity of entangled qubits through local operations and classical communication (LOCC).
no code implementations • 11 May 2022 • Osvaldo Simeone
In the current noisy intermediate-scale quantum (NISQ) era, quantum machine learning is emerging as a dominant paradigm to program gate-based quantum computers.
no code implementations • 31 Mar 2022 • Ivana Nikoloska, Osvaldo Simeone
Near-term noisy intermediate-scale quantum circuits can efficiently implement implicit probabilistic models in discrete spaces, supporting distributions that are practically infeasible to sample from using classical means.
1 code implementation • 23 Mar 2022 • Sangwoo Park, Osvaldo Simeone
An efficient data-driven prediction strategy for multi-antenna frequency-selective channels must operate based on a small number of pilot symbols.
no code implementations • 7 Mar 2022 • DaeSung Yu, Seok-Hwan Park, Osvaldo Simeone, Shlomo Shamai
Rate-Splitting Multiple Access (RSMA) for multi-user downlink operates by splitting the message for each user equipment (UE) into a private message and a set of common messages, which are simultaneously transmitted by means of superposition coding.
no code implementations • 3 Mar 2022 • Matteo Zecchin, Sangwoo Park, Osvaldo Simeone, Marios Kountouris, David Gesbert
Standard Bayesian learning is known to have suboptimal generalization capabilities under misspecification and in the presence of outliers.
no code implementations • 21 Jan 2022 • Ivana Nikoloska, Osvaldo Simeone
In this work, we study a two-layer hybrid classical-quantum classifier in which a first layer of quantum stochastic neurons implementing generalized linear models (QGLMs) is followed by a second classical combining layer.
no code implementations • 17 Jan 2022 • Sharu Theresa Jose, Osvaldo Simeone
An upper bound on the optimality gap is derived in terms of the proposed task (dis)similarity measure, two R$\'e$nyi mutual information terms between classical input and quantum embedding under source and target tasks, as well as a measure of complexity of the combined space of quantum embeddings and classifiers under the source task.
no code implementations • 12 Jan 2022 • Feng Zhu, Jingjing Zhang, Osvaldo Simeone, Xin Wang
Wall-clock convergence time and communication load are key performance metrics for the distributed implementation of stochastic gradient descent (SGD) in parameter server settings.
1 code implementation • 17 Dec 2021 • Hari Hara Suthan Chittoor, Osvaldo Simeone
This paper studies distributed Bayesian learning in a setting encompassing a central server and multiple workers by focusing on the problem of mitigating the impact of stragglers.
no code implementations • 3 Dec 2021 • Wei Jiang, Alexander M. Haimovich, Mark Govoni, Timothy Garner, Osvaldo Simeone
One approach is based on transfer learning: it first pre-trains a detector such that it works well on data collected in previously observed environments, and then it adapts the pre-trained detector to the specific current environment.
no code implementations • 23 Nov 2021 • Jinu Gong, Osvaldo Simeone, Rahif Kassab, Joonhyuk Kang
Variational particle-based Bayesian learning methods have the advantage of not being limited by the bias affecting more conventional parametric techniques.
no code implementations • 2 Nov 2021 • Bleema Rosenfeld, Osvaldo Simeone, Bipin Rajendran
Accordingly, a central problem in neuromorphic computing is training spiking neural networks (SNNs) to reproduce spatio-temporal spiking patterns in response to given spiking stimuli.
no code implementations • 19 Oct 2021 • Ivana Nikoloska, Osvaldo Simeone
Data-efficient learning algorithms are essential in many practical applications for which data collection is expensive, e. g., for the optimal deployment of wireless systems in unknown propagation scenarios.
no code implementations • 11 Oct 2021 • Sharu Theresa Jose, Osvaldo Simeone
In vertical federated learning (FL), the features of a data sample are distributed across multiple agents.
1 code implementation • 1 Oct 2021 • Sangwoo Park, Osvaldo Simeone
This paper proposes to leverage meta-learning in order to mitigate the requirements in terms of training data for channel fading prediction.
no code implementations • 9 Aug 2021 • Zhenghao Guo, Verity M. McClelland, Osvaldo Simeone, Kerry R. Mills, Zoran Cvetkovic
Results: Our experiments with neurophysiological signals substantiate the potential of the developed methodologies for detecting and quantifying information flow between EEG and EMG signals for subjects with and without significant CMC or GC, including non-linear cross-frequency interactions, and interactions across different temporal scales.
no code implementations • 4 Aug 2021 • Ivana Nikoloska, Osvaldo Simeone
In this paper, we consider the problem of power control for a wireless network with an arbitrarily time-varying topology, including the possible addition or removal of nodes.
1 code implementation • 2 Aug 2021 • Kfir M. Cohen, Sangwoo Park, Osvaldo Simeone, Shlomo Shamai
Bayesian active meta-learning is seen in experiments to significantly reduce the number of frames required to obtain efficient adaptation procedure for new frames.
1 code implementation • 20 Jun 2021 • Yunchuan Zhang, Sharu Theresa Jose, Osvaldo Simeone
Meta-learning optimizes the hyperparameters of a training procedure, such as its initialization, kernel, or learning rate, based on data sampled from a number of auxiliary tasks.
no code implementations • NeurIPS 2021 • Nicolas Skatchkovsky, Osvaldo Simeone, Hyeryung Jang
One of the key challenges in training Spiking Neural Networks (SNNs) is that target outputs typically come in the form of natural signals, such as labels for classification or images for generative models, and need to be encoded into spikes.
no code implementations • 1 Jun 2021 • Sharu Theresa Jose, Sangwoo Park, Osvaldo Simeone
Under a Bayesian formulation, assuming a well-specified model, the two contributions can be exactly expressed (for the log-loss) or bounded (for more general losses) in terms of information-theoretic quantities (Xu and Raginsky, 2020).
no code implementations • 1 Jun 2021 • Sharu Theresa Jose, Osvaldo Simeone
Machine unlearning refers to mechanisms that can remove the influence of a subset of training data upon request from a trained model without incurring the cost of re-training from scratch.
no code implementations • 2 May 2021 • Ivana Nikoloska, Osvaldo Simeone
Power control in decentralized wireless networks poses a complex stochastic optimization problem when formulated as the maximization of the average sum rate for arbitrary interference graphs.
no code implementations • 8 Apr 2021 • Jinu Gong, Osvaldo Simeone, Joonhyuk Kang
Federated Bayesian learning offers a principled framework for the definition of collaborative training algorithms that are able to quantify epistemic uncertainty and to produce trustworthy decisions.
no code implementations • 30 Mar 2021 • Seok-Hwan Park, Seongah Jeong, Jinyeop Na, Osvaldo Simeone, Shlomo Shamai
Mobile cloud and edge computing protocols make it possible to offer computationally heavy applications to mobile devices via computational offloading from devices to nearby edge servers or more powerful, but remote, cloud servers.
no code implementations • 21 Feb 2021 • Bleema Rosenfeld, Bipin Rajendran, Osvaldo Simeone
Spiking Neural Networks (SNNs) have recently gained popularity as machine learning models for on-device edge intelligence for applications such as mobile healthcare management and natural language processing due to their low power profile.
no code implementations • 19 Feb 2021 • Wei Jiang, Alexander M. Haimovich, Osvaldo Simeone
In the second approach, the transmitter and detector are trained simultaneously.
no code implementations • 5 Feb 2021 • Hyeryung Jang, Osvaldo Simeone
Spiking Neural Networks (SNNs) offer a novel computational paradigm that captures some of the efficiency of biological brains by processing through binary neural dynamic activations.
no code implementations • 29 Jan 2021 • Hong Xing, Osvaldo Simeone, Suzhi Bi
The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL).
no code implementations • 21 Jan 2021 • Sharu Theresa Jose, Osvaldo Simeone
The goal of the meta-learner is to ensure that the hyperparameters obtain a small loss when applied for training of a new task sampled from the task environment.
2 code implementations • 15 Dec 2020 • Hyeryung Jang, Nicolas Skatchkovsky, Osvaldo Simeone
Artificial Neural Network (ANN)-based inference on battery-powered devices can be made more energy-efficient by restricting the synaptic weights to be binary, hence eliminating the need to perform multiplications.
no code implementations • 25 Nov 2020 • Sharu Theresa Jose, Osvaldo Simeone
The goal of these lecture notes is to review the problem of free energy minimization as a unified framework underlying the definition of maximum entropy modelling, generalized Bayesian inference, learning with latent variables, statistical learning analysis of generalization, and local optimization.
no code implementations • 20 Nov 2020 • Iman Habibi, Effat S Emamian, Osvaldo Simeone, Ali Abdi
In this paper, computation capacity of signaling networks is introduced as a fundamental limit on signaling capability and performance of such networks.
no code implementations • 4 Nov 2020 • Sharu Theresa Jose, Osvaldo Simeone, Giuseppe Durisi
In this paper, we introduce the problem of transfer meta-learning, in which tasks are drawn from a target task environment during meta-testing that may differ from the source task environment observed during meta-training.
no code implementations • 30 Oct 2020 • Roberto G. Pacheco, Rodrigo S. Couto, Osvaldo Simeone
This work shows that the employment of a miscalibrated early-exit DNN for offloading via model partitioning can significantly decrease inference accuracy.
no code implementations • 27 Oct 2020 • Hyeryung Jang, Nicolas Skatchkovsky, Osvaldo Simeone
Then, we review learning algorithms and applications for SNNs that aim at mimicking the functionality of ANNs by detecting or generating spatial patterns in rate-encoded spiking signals.
no code implementations • 27 Oct 2020 • Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone
Inspired by the operation of biological brains, Spiking Neural Networks (SNNs) have the unique ability to detect information encoded in spatio-temporal patterns of spiking signals.
no code implementations • 27 Oct 2020 • Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone
Synergies between wireless communications and artificial intelligence are increasingly motivating research at the intersection of the two fields.
no code implementations • 21 Oct 2020 • Arezou Rezazadeh, Sharu Theresa Jose, Giuseppe Durisi, Osvaldo Simeone
Meta-learning optimizes an inductive bias---typically in the form of the hyperparameters of a base-learning algorithm---by observing data from a finite number of related tasks.
no code implementations • 13 Oct 2020 • Sharu Theresa Jose, Osvaldo Simeone
In transfer learning, training and testing data sets are drawn from different data distributions.
1 code implementation • 11 Sep 2020 • Rahif Kassab, Osvaldo Simeone
This paper introduces Distributed Stein Variational Gradient Descent (DSVGD), a non-parametric generalized Bayesian inference framework for federated learning.
2 code implementations • 3 Sep 2020 • Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone
This paper introduces a novel "all-spike" low-power solution for remote wireless inference that is based on neuromorphic sensing, Impulse Radio (IR), and Spiking Neural Networks (SNNs).
no code implementations • 5 Aug 2020 • Anakha V Babu, Osvaldo Simeone, Bipin Rajendran
We discuss a high-performance and high-throughput hardware accelerator for probabilistic Spiking Neural Networks (SNNs) based on Generalized Linear Model (GLM) neurons, that uses binary STT-RAM devices as synapses and digital CMOS logic for neurons.
Human Activity Recognition Vocal Bursts Intensity Prediction
no code implementations • 23 Jul 2020 • Hyeryung Jang, Osvaldo Simeone
It is shown that the multiple generated output samples can be used during inference to robustify decisions and to quantify uncertainty -- a feature that deterministic SNN models cannot provide.
1 code implementation • 9 Jun 2020 • Dongzhu Liu, Osvaldo Simeone
When FL is implemented in wireless systems via uncoded transmission, the channel noise can directly act as a privacy-inducing mechanism.
Information Theory Networking and Internet Architecture Signal Processing Information Theory
no code implementations • 9 May 2020 • Sharu Theresa Jose, Osvaldo Simeone
Extending the existing work for conventional learning, an upper bound on the meta-generalization gap is derived for the former class that depends on the mutual information (MI) between the output of the meta-learning algorithm and its input meta-training data.
no code implementations • 30 Apr 2020 • Adnan Mehonic, Abu Sebastian, Bipin Rajendran, Osvaldo Simeone, Eleni Vasilaki, Anthony J. Kenyon
Machine learning, particularly in the form of deep learning, has driven most of the recent fundamental developments in artificial intelligence.
no code implementations • 20 Apr 2020 • Daesung Yu, Seok-Hwan Park, Osvaldo Simeone, Shlomo Shamai
Over-the-air computation (AirComp) is an efficient solution to enable federated learning on wireless channels.
Signal Processing Information Theory Information Theory
2 code implementations • 20 Apr 2020 • Hyeryung Jang, Nicolas Skatchkovsky, Osvaldo Simeone
Networks of spiking neurons and Winner-Take-All spiking circuits (WTA-SNNs) can detect information encoded in spatio-temporal multi-valued events.
1 code implementation • 3 Mar 2020 • Sangwoo Park, Osvaldo Simeone, Joonhyuk Kang
The proposed approach is based on a meta-training phase in which the online gradient-based meta-learning of the decoder is coupled with the joint training of the encoder via the transmission of pilots and the use of a feedback link.
no code implementations • 28 Feb 2020 • Hong Xing, Osvaldo Simeone, Suzhi Bi
In this paper, wireless protocols are proposed that implement DSGD by accounting for the presence of path loss, fading, blockages, and mutual interference.
Information Theory Networking and Internet Architecture Signal Processing Information Theory
no code implementations • 3 Feb 2020 • Jin-Hyun Ahn, Osvaldo Simeone, Joonhyuk Kang
Cooperative training methods for distributed machine learning are typically based on the exchange of local gradients or local model parameters.
Signal Processing Distributed, Parallel, and Cluster Computing Information Theory Information Theory
1 code implementation • 5 Jan 2020 • Osvaldo Simeone, Sangwoo Park, Joonhyuk Kang
Machine learning methods adapt the parameters of a model, constrained to lie in a given model class, by using a fixed learning procedure based on data or active observations.
1 code implementation • 16 Dec 2019 • Jingjing Zhang, Osvaldo Simeone, Zoran Cvetkovic, Eugenio Abela, Mark Richardson
Hence, the TE quantifies the improvement, as measured by the log-loss, in the prediction of the target sequence $Y$ that can be accrued when, in addition to the past of $Y$, one also has available past samples from $X$.
no code implementations • 2 Dec 2019 • Wei Jiang, Alexander M. Haimovich, Osvaldo Simeone
An end-to-end learning approach is proposed for the joint design of transmitted waveform and detector in a radar system.
Signal Processing
1 code implementation • 22 Oct 2019 • Sangwoo Park, Osvaldo Simeone, Joonhyuk Kang
When a channel model is available, learning how to communicate on fading noisy channels can be formulated as the (unsupervised) training of an autoencoder consisting of the cascade of encoder, channel, and decoder.
3 code implementations • 21 Oct 2019 • Nicolas Skatchkovsky, Hyeryung Jang, Osvaldo Simeone
To this end, we introduce an online FL-based learning rule for networked on-device SNNs, which we refer to as FL-SNN.
no code implementations • 2 Oct 2019 • Hyeryung Jang, Osvaldo Simeone, Brian Gardner, André Grüning
The sparsity of the synaptic spiking inputs and the corresponding event-driven nature of neural processing can be leveraged by energy-efficient hardware implementations, which can offer significant energy reductions as compared to conventional artificial neural networks (ANNs).
1 code implementation • 23 Aug 2019 • Sangwoo Park, Hyeryung Jang, Osvaldo Simeone, Joonhyuk Kang
This paper considers an Internet-of-Things (IoT) scenario in which devices sporadically transmit short packets with few pilot symbols over a fading channel.
no code implementations • 5 Jul 2019 • Jin-Hyun Ahn, Osvaldo Simeone, Joonhyuk Kang
Cooperative training methods for distributed machine learning typically assume noiseless and ideal communication channels.
no code implementations • 11 Jun 2019 • Nicolas Skatchkovsky, Osvaldo Simeone
Consider a device that is connected to an edge processor via a communication channel.
no code implementations • 22 May 2019 • Jingjing Zhang, Osvaldo Simeone
Gradient-based distributed learning in Parameter Server (PS) computing architectures is subject to random delays due to straggling worker nodes, as well as to possible communication bottlenecks between PS and workers.
1 code implementation • 6 Mar 2019 • Sangwoo Park, Hyeryung Jang, Osvaldo Simeone, Joonhyuk Kang
Consider an Internet-of-Things (IoT) scenario in which devices transmit sporadically using short packets with few pilot symbols.
no code implementations • 16 Jan 2019 • Sukjong Ha, Jingjing Zhang, Osvaldo Simeone, Joonhyuk Kang
Distributed computing platforms typically assume the availability of reliable and dedicated connections among the processors.
Information Theory Information Theory
no code implementations • 10 Dec 2018 • Hyeryung Jang, Osvaldo Simeone, Brian Gardner, André Grüning
This paper aims at providing an introduction to SNNs by focusing on a probabilistic signal processing methodology that enables the direct derivation of learning rules leveraging the unique time encoding capabilities of SNNs.
no code implementations • 23 Oct 2018 • Bleema Rosenfeld, Osvaldo Simeone, Bipin Rajendran
In this work, the use of SNNs as stochastic policies is explored under an energy-efficient first-to-spike action rule, whereby the action taken by the RL agent is determined by the occurrence of the first spike among the output neurons.
no code implementations • 21 Oct 2018 • Hyeryung Jang, Osvaldo Simeone
In this work, a probabilistic model is introduced for a generalized set-up in which the synaptic time series can take values in an arbitrary alphabet and are characterized by both causal and instantaneous statistical dependencies.
no code implementations • 2 Oct 2018 • Arsham Mostaani, Osvaldo Simeone, Symeon Chatzinotas, Bjorn Ottersten
In this work, it is demonstrated that the performance of the collaborative task can be improved if the agents learn jointly how to communicate and to act, even in the presence of a delay in the communication channel.
Information Theory Multiagent Systems Information Theory
no code implementations • 22 Feb 2018 • Alireza Bagheri, Osvaldo Simeone, Bipin Rajendran
Due to the prominence of Artificial Neural Networks (ANNs) as classifiers, their sensitivity to adversarial examples, as well as robust training schemes, have been recently the subject of intense investigation.
1 code implementation • 29 Oct 2017 • Alireza Bagheri, Osvaldo Simeone, Bipin Rajendran
Third-generation neural networks, or Spiking Neural Networks (SNNs), aim at harnessing the energy efficiency of spike-domain processing by building on computing elements that operate on, and exchange, spikes.
1 code implementation • 8 Sep 2017 • Osvaldo Simeone
This monograph aims at providing an introduction to key concepts, algorithms, and theoretical results in machine learning.
no code implementations • 4 Aug 2014 • Yu Liu, Osvaldo Simeone, Alexander M. Haimovich, Wei Su
A novel Bayesian modulation classification scheme is proposed for a single-antenna system over frequency-selective fading channels.