Home

Person

Michael Christoph Gastpar

About
Privacy
Disclaimer

Graph Chatbot

Related publications (131)

Page 5 of 7

Sensing reality and communicating bits: A dangerous liaison

Martin Vetterli, Michael Christoph Gastpar, Pier Luigi Dragotti

The successful design of sensor network architectures depends crucially on the structure of the sampling, observation, and communication processes. One of the most fundamental questions concerns the sufficiency of discrete approximations in time, space, an ...

2006

On lattice codes for Gaussian interference channels

Michael Christoph Gastpar, Jingge Zhu

The usefulness of lattice codes is investigated for two-user Gaussian interference channels (IC). A coding scheme based on the compute-and-forward technique is shown to achieve the capacity region of the Gaussian IC under strong interference. The proposed ...

2015

Capacity Scaling of Cognitive Networks: Beyond Interference-Limited Communication

Michael Christoph Gastpar

The capacity scaling laws of two overlaid networks sharing the same wireless resources with different priorities are investigated. The primary network is assumed to operate in an order-optimal fashion to achieve its standalone capacity scaling law. The sec ...

2013

Caching (Bivariate) Gaussians

Michael Christoph Gastpar, Guillaume Jean Op 't Veld

Caching is a technique that alleviates networks during peak hours by transmitting partial information before a request for any is made. In a lossy setting of Gaussian databases, we study a single-user model in which good caching strategies minimize the dat ...

2020

Personalized Privacy-Preserving Distributed Learning on Heterogeneous Data

Michael Christoph Gastpar, Aditya Pradeep

One major challenge in distributed learning is to efficiently learn for each client when the data across clients is heterogeneous or non iid (not independent or identically distributed). This provides a significant challenge as the data of the other client ...

2023

Single-server Multi-message Private Information Retrieval with Side Information: the General Cases

Michael Christoph Gastpar, Su Li

The single-server multi-message private information retrieval with side information problem is studied for general cases. In this problem, K independent messages are stored at a single server. One user initially has M messages as side information and wants ...

IEEE2020

Alpha-NML Universal Predictors

Michael Christoph Gastpar, Marco Bondaschi

Inspired by Sibson’s alpha-mutual information, we introduce a new parametric class of universal predictors. This class interpolates two well-known predictors, the mixture estimator, that includes the Laplace and the Krichevsky-Trofimov predictors, and the ...

2022

Compute-and-Forward: Finding the Best Equation

Michael Christoph Gastpar, Saeid Sahraei

Compute-and-Forward is an emerging technique to deal with interference. It allows the receiver to decode a suitably chosen integer linear combination of the transmitted messages. The integer coefficients should be adapted to the channel fading state. Optim ...

2014

Locally Differentially-Private Randomized Response for Discrete Distribution Learning

Michael Christoph Gastpar, Adriano Pastore

We consider a setup in which confidential i.i.d. samples X1, . . . , Xn from an unknown finite-support distribution p are passed through n copies of a discrete privatization chan- nel (a.k.a. mechanism) producing outputs Y1, . . . , Yn. The channel law gua ...

2021

Successive Refinement of Gaussian Projections

Michael Christoph Gastpar, Guillaume Jean Op 't Veld

Successive refinement is a technique to encode a source iteratively, improving the distortion at each step. If the code rates of all steps combined can be as efficient as coding only for the final distortion in one go, then the source is said to be success ...

2014

Finite Littlestone Dimension Implies Finite Information Complexity

Michael Christoph Gastpar, Ido Nachum, Aditya Pradeep

We prove that every online learnable class of functions of Littlestone dimension d admits a learning algorithm with finite information complexity. Towards this end, we use the notion of a globally stable algorithm. Generally, the information complexity of ...

2022

Characterising high-order interdependence via entropic conjugation

Michael Christoph Gastpar

High-order phenomena are pervasive across complex systems, yet their formal characterisation remains a formidable challenge. The literature provides various information-theoretic quantities that capture high-order interdependencies, but their conceptual fo ...

2025

Real-time Prediction of Fast and Slow Delivery of Mental Commands in a Motor Imagery BCI: An Entropy-based Approach

José del Rocio Millán Ruiz, Michael Christoph Gastpar, Ricardo Andres Chavarriaga Lozano, Sareh Saeedi

Providing adaptive shared control for Brain- Computer Interfaces (BCIs) can result in better performance while reducing the user’s mental workload. In this respect, online estimation of accuracy and speed of command delivery are important factors. This stu ...

2012

A Unified Discretization Approach to Compute–Forward: From Discrete to Continuous Inputs

Michael Christoph Gastpar, Adriano Pastore, Sung Hoon Lim, Chen Feng

Compute–forward is a coding technique that enables receiver(s) in a network to directly decode one or more linear combinations of the transmitted codewords. Initial efforts focused on Gaussian channels and derived achievable rate regions via nested lattice ...

Institute of Electrical and Electronics Engineers (IEEE)2023

A Novel Centralized Strategy for Coded Caching with Non-uniform Demands

Michael Christoph Gastpar, Saeid Sahraei, Pierre Victor Xavier Quinton

Despite significant progress in the caching literature concerning the worst case and uniform average case regimes, the algorithms for caching with nonuniform demands are still at a basic stage and mostly rely on simple grouping and memory-sharing technique ...

2018

Lower-bounds on the Bayesian Risk in estimation procedures via Sibson's alpha-Mutual Information

Michael Christoph Gastpar, Amedeo Roberto Esposito

In this work, we consider the problem of parameter estimation in a Bayesian setting. We propose a new approach to lower-bounding the Bayesian risk, based on Sibson's alpha-Mutual Information. The results are then applied to specific settings of interest. A ...

IEEE2021

Towards an Algebraic Network Information Theory: Distributed Lossy Computation of Linear Functions

Michael Christoph Gastpar, Sung Hoon Lim, Adriano Pastore, Chen Feng

Consider the important special case of the K-user distributed source coding problem where the decoder only wishes to recover one or more linear combinations of the sources. The work of Körner and Marton demonstrated that, in some cases, the optimal rate re ...

2019

Multi-round computation of type-threshold functions in collocated Gaussian networks

Michael Christoph Gastpar, Chien-Yi Wang

In wireless sensor networks, various applications involve learning one or multiple functions of the measurements observed by sensors, rather than the measurements themselves. This paper focuses on the computation of type-threshold functions which include t ...

2013

Directed Information Flow and Causality in Neural Systems

Michael Christoph Gastpar

Springer Science+Business Media2022

Common Information Components Analysis

Michael Christoph Gastpar, Erixhen Sula

We give an information-theoretic interpretation of Canonical Correlation Analysis (CCA) via (relaxed) Wyner's common information. CCA permits to extract from two high-dimensional data sets low-dimensional descriptions (features) that capture the commonalit ...

IEEE2020