Building on the framework introduced by Xu and Raginksy  for supervised learning problems, we study the best achievable performance for model-based Bayesian reinforcement learning problems.
This paper studies the problem of training an ML model over decentralized systems, where data are distributed over many user devices and the learning algorithm run on-device, with the aim of relaxing the burden at a central entity/server.
Hence, we investigate the problem of jointly optimized communication efficiency and resources for FL over wireless Internet of things (IoT) networks.
Alternating direction method of multipliers (ADMM) has a structure that allows for decentralized implementation, and has shown faster convergence than gradient descent based methods.
To ensure parameter privacy, we propose a filter design framework which consists of two components: a randomizer and a nonlinear transformation.
We show that using artificial neural networks to predict the required order of an ordered statistics based decoder helps in reducing the average complexity and hence the latency of the decoder.
In this paper, we introduce a multi-objective optimization framework for the optimal design of URLLC in the presence of decoding complexity constraints.
Information Theory Information Theory
Regarding the Nash equilibrium, we explicitly characterize affine equilibria for the single-stage setup and show that the optimal encoder (resp.
Optimization and Control Information Theory Information Theory
In an intelligent transportation system, the effects and relations of traffic flow at different points in a network are valuable features which can be exploited for control system design and traffic forecasting.
We use a combination of random weights and rectified linear unit (ReLU) activation function to add a ReLU dense (ReDense) layer to the trained neural network such that it can achieve a lower training loss.
In this work, we unify several expected generalization error bounds based on random subsets using the framework developed by Hellstr\"om and Durisi .
A class of mini-batch stochastic alternating direction method of multipliers (ADMM) algorithms is explored to develop the distributed learning model.
We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers).
Cell-free networks are considered as a promising distributed network architecture to satisfy the increasing number of users and high rate expectations in beyond-5G systems.
The estimation of mutual information (MI) or conditional mutual information (CMI) from a set of samples is a long-standing problem.
In this work, we exploit an asynchronous computing framework namely ARock to learn a deep neural network called self-size estimating feedforward neural network (SSFN) in a decentralized scenario.
We show that the proposed architecture is norm-preserving and provides an invertible feature vector, and therefore, can be used to reduce the training cost of any other learning method which employs linear projection to estimate the target.
Inter-operator spectrum sharing in millimeter-wave bands has the potential of substantially increasing the spectrum utilization and providing a larger bandwidth to individual user equipment at the expense of increasing inter-operator interference.
In this paper, we (i) present a general family of Lagrangians which allow for the exploration of the IB curve in all scenarios; (ii) provide the exact one-to-one mapping between the Lagrange multiplier and the desired compression rate $r$ for known IB curve shapes; and (iii) show we can approximately obtain a specific compression level with the convex IB Lagrangian for both known and unknown IB curve shapes.
We explore the use of traditional and contemporary hidden Markov models (HMMs) for sequential physiological data analysis and sepsis prediction in preterm infants.
To determine the caching scheme for decentralized caching networks, the content preference learning problem based on mobility prediction is studied.
We design a self size-estimating feed-forward network (SSFN) using a joint optimization approach for estimation of number of layers, number of nodes and learning of weight matrices.
In this paper, we obtain generic bounds on the variances of estimation and prediction errors in time series analysis via an information-theoretic approach.
We summarize our recent findings, where we proposed a framework for learning a Kolmogorov model, for a collection of binary random variables.
The lack of mathematical tractability of Deep Neural Networks (DNNs) has hindered progress towards having a unified convergence analysis of training algorithms, in the general setting.
The developed network is expected to show good generalization power due to appropriate regularization and use of random weights in the layers.
We address some theoretical guarantees for Schatten-$p$ quasi-norm minimization ($p \in (0, 1]$) in recovering low-rank matrices from compressed linear measurements.