Search Results for author: Mikael Skoglund

Found 33 papers, 5 papers with code

An Information-Theoretic Analysis of Bayesian Reinforcement Learning

no code implementations18 Jul 2022 Amaury Gouverneur, Borja Rodríguez-Gálvez, Tobias J. Oechtering, Mikael Skoglund

Building on the framework introduced by Xu and Raginksy [1] for supervised learning problems, we study the best achievable performance for model-based Bayesian reinforcement learning problems.


Asynchronous Parallel Incremental Block-Coordinate Descent for Decentralized Machine Learning

no code implementations7 Feb 2022 Hao Chen, Yu Ye, Ming Xiao, Mikael Skoglund

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.

BIG-bench Machine Learning

Federated Learning over Wireless IoT Networks with Optimized Communication and Resources

no code implementations22 Oct 2021 Hao Chen, Shaocheng Huang, Deyou Zhang, Ming Xiao, Mikael Skoglund, H. Vincent Poor

Hence, we investigate the problem of jointly optimized communication efficiency and resources for FL over wireless Internet of things (IoT) networks.

Federated Learning

Generalized Talagrand Inequality for Sinkhorn Distance using Entropy Power Inequality

no code implementations17 Sep 2021 Shuchan Wang, Photios A. Stavrou, Mikael Skoglund

We evaluate for a wide variety of distributions this term whereas for Gaussian and i. i. d.

Adaptive Stochastic ADMM for Decentralized Reinforcement Learning in Edge Industrial IoT

no code implementations30 Jun 2021 Wanlu Lei, Yu Ye, Ming Xiao, Mikael Skoglund, Zhu Han

Alternating direction method of multipliers (ADMM) has a structure that allows for decentralized implementation, and has shown faster convergence than gradient descent based methods.

Decision Making Edge-computing +1

A Model Randomization Approach to Statistical Parameter Privacy

no code implementations22 May 2021 Ehsan Nekouei, Henrik Sandberg, Mikael Skoglund, Karl H. Johansson

To ensure parameter privacy, we propose a filter design framework which consists of two components: a randomizer and a nonlinear transformation.

A Learning-Based Approach to Address Complexity-Reliability Tradeoff in OS Decoders

no code implementations5 Mar 2021 Baptiste Cavarec, Hasan Basri Celebi, Mats Bengtsson, Mikael Skoglund

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.

A Multi-Objective Optimization Framework for URLLC with Decoding Complexity Constraints

no code implementations24 Feb 2021 Hasan Basri Celebi, Antonios Pitarokoilis, Mikael Skoglund

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

Quadratic Signaling Games with Channel Combining Ratio

no code implementations3 Feb 2021 Serkan Sarıtaş, Photios A. Stavrou, Ragnar Thobaben, Mikael Skoglund

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

Causality Graph of Vehicular Traffic Flow

no code implementations23 Nov 2020 Sina Molavipour, Germán Bassi, Mladen Čičić, Mikael Skoglund, Karl Henrik Johansson

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.

A ReLU Dense Layer to Improve the Performance of Neural Networks

1 code implementation22 Oct 2020 Alireza M. Javid, Sandipan Das, Mikael Skoglund, Saikat Chatterjee

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.

On Random Subset Generalization Error Bounds and the Stochastic Gradient Langevin Dynamics Algorithm

no code implementations21 Oct 2020 Borja Rodríguez-Gálvez, Germán Bassi, Ragnar Thobaben, Mikael Skoglund

In this work, we unify several expected generalization error bounds based on random subsets using the framework developed by Hellstr\"om and Durisi [1].

Coded Stochastic ADMM for Decentralized Consensus Optimization with Edge Computing

no code implementations2 Oct 2020 Hao Chen, Yu Ye, Ming Xiao, Mikael Skoglund, H. Vincent Poor

A class of mini-batch stochastic alternating direction method of multipliers (ADMM) algorithms is explored to develop the distributed learning model.


A Low Complexity Decentralized Neural Net with Centralized Equivalence using Layer-wise Learning

no code implementations29 Sep 2020 Xinyue Liang, Alireza M. Javid, Mikael Skoglund, Saikat Chatterjee

We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers).

Decentralized Beamforming Design for Intelligent Reflecting Surface-enhanced Cell-free Networks

no code implementations22 Jun 2020 Shaocheng Huang, Yu Ye, Ming Xiao, H. Vincent Poor, Mikael Skoglund

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.

Neural Estimators for Conditional Mutual Information Using Nearest Neighbors Sampling

1 code implementation12 Jun 2020 Sina Molavipour, Germán Bassi, Mikael Skoglund

The estimation of mutual information (MI) or conditional mutual information (CMI) from a set of samples is a long-standing problem.

A Variational Approach to Privacy and Fairness

2 code implementations11 Jun 2020 Borja Rodríguez-Gálvez, Ragnar Thobaben, Mikael Skoglund

In this article, we propose a new variational approach to learn private and/or fair representations.

Fairness Representation Learning

Upper Bounds on the Generalization Error of Private Algorithms for Discrete Data

no code implementations12 May 2020 Borja Rodríguez-Gálvez, Germán Bassi, Mikael Skoglund

In this work, we study the generalization capability of algorithms from an information-theoretic perspective.

Asynchronous Decentralized Learning of a Neural Network

no code implementations10 Apr 2020 Xinyue Liang, Alireza M. Javid, Mikael Skoglund, Saikat Chatterjee

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.

High-dimensional Neural Feature Design for Layer-wise Reduction of Training Cost

no code implementations29 Mar 2020 Alireza M. Javid, Arun Venkitaraman, Mikael Skoglund, Saikat Chatterjee

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.

A Hybrid Model-based and Data-driven Approach to Spectrum Sharing in mmWave Cellular Networks

no code implementations19 Mar 2020 Hossein S. Ghadikolaei, Hadi Ghauch, Gabor Fodor, Mikael Skoglund, Carlo Fischione

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.

The Convex Information Bottleneck Lagrangian

2 code implementations25 Nov 2019 Borja Rodríguez Gálvez, Ragnar Thobaben, Mikael Skoglund

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.

Conditional Mutual Information Neural Estimator

no code implementations6 Nov 2019 Sina Molavipour, Germán Bassi, Mikael Skoglund

Several recent works in communication systems have proposed to leverage the power of neural networks in the design of encoders and decoders.

Hidden Markov Models for sepsis detection in preterm infants

no code implementations30 Oct 2019 Antoine Honore, Dong Liu, David Forsberg, Karen Coste, Eric Herlenius, Saikat Chatterjee, Mikael Skoglund

We explore the use of traditional and contemporary hidden Markov models (HMMs) for sequential physiological data analysis and sepsis prediction in preterm infants.

Mobility-aware Content Preference Learning in Decentralized Caching Networks

no code implementations22 Aug 2019 Yu Ye, Ming Xiao, Mikael Skoglund

To determine the caching scheme for decentralized caching networks, the content preference learning problem based on mobility prediction is studied.

Multi-Task Learning

SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials

no code implementations17 May 2019 Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Shumpei Kikuta, Dong Liu, Partha P. Mitra, Mikael Skoglund

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.

Image Classification

Decentralized Multi-Task Learning Based on Extreme Learning Machines

no code implementations25 Apr 2019 Yu Ye, Ming Xiao, Mikael Skoglund

We first present the ELM based MTL problem in the centralized setting, which is solved by the proposed MTL-ELM algorithm.

Multi-Task Learning

Generic Variance Bounds on Estimation and Prediction Errors in Time Series Analysis: An Entropy Perspective

no code implementations9 Apr 2019 Song Fang, Mikael Skoglund, Karl Henrik Johansson, Hideaki Ishii, Quanyan Zhu

In this paper, we obtain generic bounds on the variances of estimation and prediction errors in time series analysis via an information-theoretic approach.

Gaussian Processes Time Series +1

Learning Kolmogorov Models for Binary Random Variables

no code implementations6 Jun 2018 Hadi Ghauch, Mikael Skoglund, Hossein Shokri-Ghadikolaei, Carlo Fischione, Ali H. Sayed

We summarize our recent findings, where we proposed a framework for learning a Kolmogorov model, for a collection of binary random variables.

BIG-bench Machine Learning Interpretable Machine Learning +1

A Unified Framework for Training Neural Networks

no code implementations23 May 2018 Hadi Ghauch, Hossein Shokri-Ghadikolaei, Carlo Fischione, Mikael Skoglund

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.

General Classification

Progressive Learning for Systematic Design of Large Neural Networks

1 code implementation23 Oct 2017 Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi, Partha P. Mitra, Mikael Skoglund

The developed network is expected to show good generalization power due to appropriate regularization and use of random weights in the layers.

Performance Guarantees for Schatten-$p$ Quasi-Norm Minimization in Recovery of Low-Rank Matrices

no code implementations14 Jul 2014 Mohammadreza Malek-Mohammadi, Massoud Babaie-Zadeh, Mikael Skoglund

We address some theoretical guarantees for Schatten-$p$ quasi-norm minimization ($p \in (0, 1]$) in recovering low-rank matrices from compressed linear measurements.

Automated Theorem Proving

Cannot find the paper you are looking for? You can Submit a new open access paper.