arXiv subjects

Jalil Taghia

Publications and source records attributed to Jalil Taghia.

8 recordsLinked to original sources

arXiv2025

Multi-Generator Continual Learning for Robust Delay Prediction in 6G

In future 6G networks, dependable networks will enable telecommunication services such as remote control of robots or vehicles with strict requirements on end-to-end network performance in terms of delay, delay variation, tail distributions, and throughput. With respect to such networks, it is paramount to be able to determine what performance level the network segment can guarantee at a given point in time. One promising approach is to use predictive models trained using machine learning (ML). Predicting performance metrics such as one-way delay (OWD), in a timely manner, provides valuable insights for the network, user equipments (UEs), and applications to address performance trends, deviations, and violations. Over the course of time, a dynamic network environment results in distributional shifts, which causes catastrophic forgetting and drop of ML model performance. In continual learning (CL), the model aims to achieve a balance between stability and plasticity, enabling new information to be learned while preserving previously learned knowledge. In this paper, we target on the challenges of catastrophic forgetting of OWD prediction model. We propose a novel approach which introducing the concept of multi-generator for the state-of-the-art CL generative replay framework, along with tabular variational autoencoders (TVAE) as generators. The domain knowledge of UE capabilities is incorporated into the learning process for determining generator setup and relevance. The proposed approach is evaluated across a diverse set of scenarios with data that is collected in a realistic 5G testbed, demonstrating its outstanding performance in comparison to baselines.

cs.NI↗

arXiv2023

Variational Elliptical Processes

We present elliptical processes, a family of non-parametric probabilistic models that subsume Gaussian processes and Student's t processes. This generalization includes a range of new heavy-tailed behaviors while retaining computational tractability. Elliptical processes are based on a representation of elliptical distributions as a continuous mixture of Gaussian distributions. We parameterize this mixture distribution as a spline normalizing flow, which we train using variational inference. The proposed form of the variational posterior enables a sparse variational elliptical process applicable to large-scale problems. We highlight advantages compared to Gaussian processes through regression and classification experiments. Elliptical processes can supersede Gaussian processes in several settings, including cases where the likelihood is non-Gaussian or when accurate tail modeling is essential.

cs.LG↗

arXiv2022

Evolving 5G: ANIARA, an Edge-Cloud perspective

Emerging use-cases like smart manufacturing and smart cities pose challenges in terms of latency, which cannot be satisfied by traditional centralized networks. Edge networks, which bring computational capacity closer to the users/clients, are a promising solution for supporting these critical low latency services. Different from traditional centralized networks, the edge is distributed by nature and is usually equipped with limited connectivity and compute capacity. This creates a complex network to handle, subject to failures of different natures, that requires novel solutions to work in practice. To reduce complexity, more lightweight solutions are needed for containerization as well as smart monitoring strategies with reduced overhead. Orchestration strategies should provide reliable resource slicing with limited resources, and intelligent scaling while preserving data privacy in a distributed fashion. Power management is also critical, as providing and managing a large amount of power at the edge is unprecedented.

cs.NI↗

arXiv2020

The Elliptical Processes: a Family of Fat-tailed Stochastic Processes

We present the elliptical processes -- a family of non-parametric probabilistic models that subsumes the Gaussian process and the Student-t process. This generalization includes a range of new fat-tailed behaviors yet retains computational tractability. We base the elliptical processes on a representation of elliptical distributions as a continuous mixture of Gaussian distributions and derive closed-form expressions for the marginal and conditional distributions. We perform numerical experiments on robust regression using an elliptical process defined by a piecewise constant mixing distribution, and show advantages compared with a Gaussian process. The elliptical processes may become a replacement for Gaussian processes in several settings, including when the likelihood is not Gaussian or when accurate tail modeling is critical.

stat.ME↗

arXiv2020

On the Convergence of Extended Variational Inference for Non-Gaussian Statistical Models

Variational inference (VI) is a widely used framework in Bayesian estimation. For most of the non-Gaussian statistical models, it is infeasible to find an analytically tractable solution to estimate the posterior distributions of the parameters. Recently, an improved framework, namely the extended variational inference (EVI), has been introduced and applied to derive analytically tractable solution by employing lower-bound approximation to the variational objective function. Two conditions required for EVI implementation, namely the weak condition and the strong condition, are discussed and compared in this paper. In practical implementation, the convergence of the EVI depends on the selection of the lower-bound approximation, no matter with the weak condition or the strong condition. In general, two approximation strategies, the single lower-bound (SLB) approximation and the multiple lower-bounds (MLB) approximation, can be applied to carry out the lower-bound approximation. To clarify the differences between the SLB and the MLB, we will also discuss the convergence properties of the aforementioned two approximations. Extensive comparisons are made based on some existing EVI-based non-Gaussian statistical models. Theoretical analysis are conducted to demonstrate the differences between the weak and the strong conditions. Qualitative and quantitative experimental results are presented to show the advantages of the SLB approximation.

stat.ML↗

arXiv2020

The NIGENS General Sound Events Database

Computational auditory scene analysis is gaining interest in the last years. Trailing behind the more mature field of speech recognition, it is particularly general sound event detection that is attracting increasing attention. Crucial for training and testing reasonable models is having available enough suitable data -- until recently, general sound event databases were hardly found. We release and present a database with 714 wav files containing isolated high quality sound events of 14 different types, plus 303 `general' wav files of anything else but these 14 types. All sound events are strongly labeled with perceptual on- and offset times, paying attention to omitting in-between silences. The amount of isolated sound events, the quality of annotations, and the particular general sound class distinguish NIGENS from other databases.

cs.SD↗

arXiv2019

Conditionally Independent Multiresolution Gaussian Processes

The multiresolution Gaussian process (GP) has gained increasing attention as a viable approach towards improving the quality of approximations in GPs that scale well to large-scale data. Most of the current constructions assume full independence across resolutions. This assumption simplifies the inference, but it underestimates the uncertainties in transitioning from one resolution to another. This in turn results in models which are prone to overfitting in the sense of excessive sensitivity to the chosen resolution, and predictions which are non-smooth at the boundaries. Our contribution is a new construction which instead assumes conditional independence among GPs across resolutions. We show that relaxing the full independence assumption enables robustness against overfitting, and that it delivers predictions that are smooth at the boundaries. Our new model is compared against current state of the art on 2 synthetic and 9 real-world datasets. In most cases, our new conditionally independent construction performed favorably when compared against models based on the full independence assumption. In particular, it exhibits little to no signs of overfitting.

stat.ML↗

arXiv2019

Constructing the Matrix Multilayer Perceptron and its Application to the VAE

Like most learning algorithms, the multilayer perceptrons (MLP) is designed to learn a vector of parameters from data. However, in certain scenarios we are interested in learning structured parameters (predictions) in the form of symmetric positive definite matrices. Here, we introduce a variant of the MLP, referred to as the matrix MLP, that is specialized at learning symmetric positive definite matrices. We also present an application of the model within the context of the variational autoencoder (VAE). Our formulation of the VAE extends the vanilla formulation to the cases where the recognition and the generative networks can be from the parametric family of distributions with dense covariance matrices. Two specific examples are discussed in more detail: the dense covariance Gaussian and its generalization, the power exponential distribution. Our new developments are illustrated using both synthetic and real data.

stat.ML↗