arXiv subjects

Osvaldo Simeone

Publications and source records attributed to Osvaldo Simeone.

At least 217 records · Page 12Linked to original sources

arXiv2021

An Information-Theoretic Analysis of the Impact of Task Similarity on Meta-Learning

Meta-learning aims at optimizing the hyperparameters of a model class or training algorithm from the observation of data from a number of related tasks. Following the setting of Baxter [1], the tasks are assumed to belong to the same task environment, which is defined by a distribution over the space of tasks and by per-task data distributions. The statistical properties of the task environment thus dictate the similarity of the tasks. 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. The difference between the resulting average loss, known as meta-population loss, and the corresponding empirical loss measured on the available data from related tasks, known as meta-generalization gap, is a measure of the generalization capability of the meta-learner. In this paper, we present novel information-theoretic bounds on the average absolute value of the meta-generalization gap. Unlike prior work [2], our bounds explicitly capture the impact of task relatedness, the number of tasks, and the number of data samples per task on the meta-generalization gap. Task similarity is gauged via the Kullback-Leibler (KL) and Jensen-Shannon (JS) divergences. We illustrate the proposed bounds on the example of ridge regression with meta-learned bias.

cs.LG↗

arXiv2021

Fast Power Control Adaptation via Meta-Learning for Random Edge Graph Neural Networks

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. Recent work has introduced data-driven design methods that leverage graph neural network (GNN) to efficiently parametrize the power control policy mapping channel state information (CSI) to the power vector. The specific GNN architecture, known as random edge GNN (REGNN), defines a non-linear graph convolutional architecture whose spatial weights are tied to the channel coefficients, enabling a direct adaption to channel conditions. This paper studies the higher-level problem of enabling fast adaption of the power control policy to time-varying topologies. To this end, we apply first-order meta-learning on data from multiple topologies with the aim of optimizing for a few-shot adaptation to new network configurations.

cs.IT↗

arXiv2021

Spiking Neural Networks -- Part II: Detecting Spatio-Temporal Patterns

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. Examples of data types requiring spatio-temporal processing include logs of time stamps, e.g., of tweets, and outputs of neural prostheses and neuromorphic sensors. In this paper, the second of a series of three review papers on SNNs, we first review models and training algorithms for the dominant approach that considers SNNs as a Recurrent Neural Network (RNN) and adapt learning rules based on backpropagation through time to the requirements of SNNs. In order to tackle the non-differentiability of the spiking mechanism, state-of-the-art solutions use surrogate gradients that approximate the threshold activation function with a differentiable function. Then, we describe an alternative approach that relies on probabilistic models for spiking neurons, allowing the derivation of local learning rules via stochastic estimates of the gradient. Finally, experiments are provided for neuromorphic data sets, yielding insights on accuracy and convergence under different SNN models.

cs.NE↗

arXiv2021

Bayesian Variational Federated Learning and Unlearning in Decentralized Networks

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. Upon the completion of collaborative training, an agent may decide to exercise her legal "right to be forgotten", which calls for her contribution to the jointly trained model to be deleted and discarded. This paper studies federated learning and unlearning in a decentralized network within a Bayesian framework. It specifically develops federated variational inference (VI) solutions based on the decentralized solution of local free energy minimization problems within exponential-family models and on local gossip-driven communication. The proposed protocols are demonstrated to yield efficient unlearning mechanisms.

cs.LG↗

arXiv2021

Federated Generalized Bayesian Learning via Distributed Stein Variational Gradient Descent

This paper introduces Distributed Stein Variational Gradient Descent (DSVGD), a non-parametric generalized Bayesian inference framework for federated learning. DSVGD maintains a number of non-random and interacting particles at a central server to represent the current iterate of the model global posterior. The particles are iteratively downloaded and updated by one of the agents with the end goal of minimizing the global free energy. By varying the number of particles, DSVGD enables a flexible trade-off between per-iteration communication load and number of communication rounds. DSVGD is shown to compare favorably to benchmark frequentist and Bayesian federated learning strategies, also scheduling a single device per iteration, in terms of accuracy and scalability with respect to the number of agents, while also providing well-calibrated, and hence trustworthy, predictions.

cs.LG↗

arXiv2021

Collaborative Cloud and Edge Mobile Computing in C-RAN Systems with Minimal End-to-End Latency

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. Previous work assumed that computational tasks can be fractionally offloaded at both cloud processor (CP) and at a local edge node (EN) within a conventional Distributed Radio Access Network (D-RAN) that relies on non-cooperative ENs equipped with one-way uplink fronthaul connection to the cloud. In this paper, we propose to integrate collaborative fractional computing across CP and ENs within a Cloud RAN (C-RAN) architecture with finite-capacity two-way fronthaul links. Accordingly, tasks offloaded by a mobile device can be partially carried out at an EN and the CP, with multiple ENs communicating with a common CP to exchange data and computational outcomes while allowing for centralized precoding and decoding. Unlike prior work, we investigate joint optimization of computing and communication resources, including wireless and fronthaul segments, to minimize the end-to-end latency by accounting for a two-way uplink and downlink transmission. The problem is tackled by using fractional programming (FP) and matrix FP. Extensive numerical results validate the performance gain of the proposed architecture as compared to the previously studied D-RAN solution.

eess.SP↗

arXiv2021

Meta-ViterbiNet: Online Meta-Learned Viterbi Equalization for Non-Stationary Channels

Deep neural networks (DNNs) based digital receivers can potentially operate in complex environments. However, the dynamic nature of communication channels implies that in some scenarios, DNN-based receivers should be periodically retrained in order to track temporal variations in the channel conditions. To this aim, frequent transmissions of lengthy pilot sequences are generally required, at the cost of substantial overhead. In this work we propose a DNN-aided symbol detector, Meta-ViterbiNet, that tracks channel variations with reduced overhead by integrating three complementary techniques: 1) We leverage domain knowledge to implement a model-based/data-driven equalizer, ViterbiNet, that operates with a relatively small number of trainable parameters; 2) We tailor a meta-learning procedure to the symbol detection problem, optimizing the hyperparameters of the learning algorithm to facilitate rapid online adaptation; and 3) We adopt a decision-directed approach based on coded communications to enable online training with short-length pilot blocks. Numerical results demonstrate that Meta-ViterbiNet operates accurately in rapidly-varying channels, outperforming the previous best approach, based on ViterbiNet or conventional recurrent neural networks without meta-learning, by a margin of up to 0.6dB in bit error rate in various challenging scenarios.

cs.IT↗

arXiv2021

Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning

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. In such highly personalized use cases, it is important for the model to be able to adapt to the unique features of an individual with only a minimal amount of training data. Meta-learning has been proposed as a way to train models that are geared towards quick adaptation to new tasks. The few existing meta-learning solutions for SNNs operate offline and require some form of backpropagation that is incompatible with the current neuromorphic edge-devices. In this paper, we propose an online-within-online meta-learning rule for SNNs termed OWOML-SNN, that enables lifelong learning on a stream of tasks, and relies on local, backprop-free, nested updates.

cs.NE↗

arXiv2021

Joint Design of Radar Waveform and Detector via End-to-end Learning with Waveform Constraints

The problem of data-driven joint design of transmitted waveform and detector in a radar system is addressed in this paper. We propose two novel learning-based approaches to waveform and detector design based on end-to-end training of the radar system. The first approach consists of alternating supervised training of the detector for a fixed waveform and reinforcement learning of the transmitter for a fixed detector. In the second approach, the transmitter and detector are trained simultaneously. Various operational waveform constraints, such as peak-to-average-power ratio (PAR) and spectral compatibility, are incorporated into the design. Unlike traditional radar design methods that rely on rigid mathematical models with limited applicability, it is shown that radar learning can be robustified by training the detector with synthetic data generated from multiple statistical models of the environment. Theoretical considerations and results show that the proposed methods are capable of adapting the transmitted waveform to environmental conditions while satisfying design constraints.

eess.SP↗

arXiv2021

Conditional Mutual Information-Based Generalization Bound for Meta Learning

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. This paper presents an information-theoretic bound on the generalization performance of any given meta-learner, which builds on the conditional mutual information (CMI) framework of Steinke and Zakynthinou (2020). In the proposed extension to meta-learning, the CMI bound involves a training \textit{meta-supersample} obtained by first sampling $2N$ independent tasks from the task environment, and then drawing $2M$ independent training samples for each sampled task. The meta-training data fed to the meta-learner is modelled as being obtained by randomly selecting $N$ tasks from the available $2N$ tasks and $M$ training samples per task from the available $2M$ training samples per task. The resulting bound is explicit in two CMI terms, which measure the information that the meta-learner output and the base-learner output provide about which training data are selected, given the entire meta-supersample. Finally, we present a numerical example that illustrates the merits of the proposed bound in comparison to prior information-theoretic bounds for meta-learning.

cs.LG↗

arXiv2021

Multi-Sample Online Learning for Spiking Neural Networks based on Generalized Expectation Maximization

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. Probabilistic SNN models are typically trained to maximize the likelihood of the desired outputs by using unbiased estimates of the log-likelihood gradients. While prior work used single-sample estimators obtained from a single run of the network, this paper proposes to leverage multiple compartments that sample independent spiking signals while sharing synaptic weights. The key idea is to use these signals to obtain more accurate statistical estimates of the log-likelihood training criterion, as well as of its gradient. The approach is based on generalized expectation-maximization (GEM), which optimizes a tighter approximation of the log-likelihood using importance sampling. The derived online learning algorithm implements a three-factor rule with global per-compartment learning signals. Experimental results on a classification task on the neuromorphic MNIST-DVS data set demonstrate significant improvements in terms of log-likelihood, accuracy, and calibration when increasing the number of compartments used for training and inference.

cs.LG↗

arXiv2021

Calibration-Aided Edge Inference Offloading via Adaptive Model Partitioning of Deep Neural Networks

Mobile devices can offload deep neural network (DNN)-based inference to the cloud, overcoming local hardware and energy limitations. However, offloading adds communication delay, thus increasing the overall inference time, and hence it should be used only when needed. An approach to address this problem consists of the use of adaptive model partitioning based on early-exit DNNs. Accordingly, the inference starts at the mobile device, and an intermediate layer estimates the accuracy: If the estimated accuracy is sufficient, the device takes the inference decision; Otherwise, the remaining layers of the DNN run at the cloud. Thus, the device offloads the inference to the cloud only if it cannot classify a sample with high confidence. This offloading requires a correct accuracy prediction at the device. Nevertheless, DNNs are typically miscalibrated, providing overconfident decisions. This work shows that the employment of a miscalibrated early-exit DNN for offloading via model partitioning can significantly decrease inference accuracy. In contrast, we argue that implementing a calibration algorithm prior to deployment can solve this problem, allowing for more reliable offloading decisions.

cs.LG↗

arXiv2021

Joint Source-Channel Coding for Semantics-Aware Grant-Free Radio Access in IoT Fog Networks

A fog-radio access network (F-RAN) architecture is studied for an Internet-of-Things (IoT) system in which wireless sensors monitor a number of multi-valued events and transmit in the uplink using grant-free random access to multiple edge nodes (ENs). Each EN is connected to a central processor (CP) via a finite-capacity fronthaul link. In contrast to conventional information-agnostic protocols based on separate source-channel (SSC) coding, where each device uses a separate codebook, this paper considers an information-centric approach based on joint source-channel (JSC) coding via a non-orthogonal generalization of type-based multiple access (TBMA). By leveraging the semantics of the observed signals, all sensors measuring the same event share the same codebook (with non-orthogonal codewords), and all such sensors making the same local estimate of the event transmit the same codeword. The F-RAN architecture directly detects the events values without first performing individual decoding for each device. Cloud and edge detection schemes based on Bayesian message passing are designed and trade-offs between cloud and edge processing are assessed.

cs.IT↗

arXiv2021

Information-Theoretic Bounds on Transfer Generalization Gap Based on Jensen-Shannon Divergence

In transfer learning, training and testing data sets are drawn from different data distributions. The transfer generalization gap is the difference between the population loss on the target data distribution and the training loss. The training data set generally includes data drawn from both source and target distributions. This work presents novel information-theoretic upper bounds on the average transfer generalization gap that capture $(i)$ the domain shift between the target data distribution $P'_Z$ and the source distribution $P_Z$ through a two-parameter family of generalized $(α_1,α_2)$-Jensen-Shannon (JS) divergences; and $(ii)$ the sensitivity of the transfer learner output $W$ to each individual sample of the data set $Z_i$ via the mutual information $I(W;Z_i)$. For $α_1 \in (0,1)$, the $(α_1,α_2)$-JS divergence can be bounded even when the support of $P_Z$ is not included in that of $P'_Z$. This contrasts the Kullback-Leibler (KL) divergence $D_{KL}(P_Z||P'_Z)$-based bounds of Wu et al. [1], which are vacuous under this assumption. Moreover, the obtained bounds hold for unbounded loss functions with bounded cumulant generating functions, unlike the $ϕ$-divergence based bound of Wu et al. [1]. We also obtain new upper bounds on the average transfer excess risk in terms of the $(α_1,α_2)$-JS divergence for empirical weighted risk minimization (EWRM), which minimizes the weighted average training losses over source and target data sets. Finally, we provide a numerical example to illustrate the merits of the introduced bounds.

cs.LG↗

arXiv2021

Single-RF Multi-User Communication Through Reconfigurable Intelligent Surfaces: An Information-Theoretic Analysis

Reconfigurable intelligent surfaces (RISs) are typically used in multi-user systems to mitigate interference among active transmitters. In contrast, this paper studies a setting with a conventional active encoder as well as a passive encoder that modulates the reflection pattern of the RIS. The RIS hence serves the dual purpose of improving the rate of the active encoder and of enabling communication from the second encoder. The capacity region is characterized, and information-theoretic insights regarding the trade-offs between the rates of the two encoders are derived by focusing on the high- and low-power regimes.

cs.IT↗

arXiv2021

Coded Computing and Cooperative Transmission for Wireless Distributed Matrix Multiplication

Consider a multi-cell mobile edge computing network, in which each user wishes to compute the product of a user-generated data matrix with a network-stored matrix. This is done through task offloading by means of input uploading, distributed computing at edge nodes (ENs), and output downloading. Task offloading may suffer long delay since servers at some ENs may be straggling due to random computation time, and wireless channels may experience severe fading and interference. This paper aims to investigate the interplay among upload, computation, and download latencies during the offloading process in the high signal-to-noise ratio regime from an information-theoretic perspective. A policy based on cascaded coded computing and on coordinated and cooperative interference management in uplink and downlink is proposed and proved to be approximately optimal for a sufficiently large upload time. By investing more time in uplink transmission, the policy creates data redundancy at the ENs, which can reduce the computation time, by enabling the use of coded computing, as well as the download time via transmitter cooperation. Moreover, the policy allows computation time to be traded for download time. Numerical examples demonstrate that the proposed policy can improve over existing schemes by significantly reducing the end-to-end execution time.

cs.IT↗

arXiv2021

Information-Theoretic Generalization Bounds for Meta-Learning and Applications

Meta-learning, or "learning to learn", refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key performance measure for meta-learning is the meta-generalization gap, that is, the difference between the average loss measured on the meta-training data and on a new, randomly selected task. This paper presents novel information-theoretic upper bounds on the meta-generalization gap. Two broad classes of meta-learning algorithms are considered that uses either separate within-task training and test sets, like MAML, or joint within-task training and test sets, like Reptile. 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. For the latter, the derived bound includes an additional MI between the output of the per-task learning procedure and corresponding data set to capture within-task uncertainty. Tighter bounds are then developed, under given technical conditions, for the two classes via novel Individual Task MI (ITMI) bounds. Applications of the derived bounds are finally discussed, including a broad class of noisy iterative algorithms for meta-learning.

cs.LG↗

arXiv2021

Multi-Sample Online Learning for Probabilistic Spiking Neural Networks

Spiking Neural Networks (SNNs) capture some of the efficiency of biological brains for inference and learning via the dynamic, online, event-driven processing of binary time series. Most existing learning algorithms for SNNs are based on deterministic neuronal models, such as leaky integrate-and-fire, and rely on heuristic approximations of backpropagation through time that enforce constraints such as locality. In contrast, probabilistic SNN models can be trained directly via principled online, local, update rules that have proven to be particularly effective for resource-constrained systems. This paper investigates another advantage of probabilistic SNNs, namely their capacity to generate independent outputs when queried over the same input. 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. Furthermore, they can be leveraged for training in order to obtain more accurate statistical estimates of the log-loss training criterion, as well as of its gradient. Specifically, this paper introduces an online learning rule based on generalized expectation-maximization (GEM) that follows a three-factor form with global learning signals and is referred to as GEM-SNN. Experimental results on structured output memorization and classification on a standard neuromorphic data set demonstrate significant improvements in terms of log-likelihood, accuracy, and calibration when increasing the number of samples used for inference and training.

cs.LG↗