Personne

Michael Christoph Gastpar

Publications associées (232)

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

Distributed Lossy Computation with Structured Codes: From Discrete to Continuous Sources

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

This paper considers the problem of distributed lossy compression where the goal is to recover one or more linear combinations of the sources at the decoder, subject to distortion constraints. For certain configurations, it is known that codes with algebra ...

2023

Differential Entropy of the Conditional Expectation Under Additive Gaussian Noise

Michael Christoph Gastpar, Alper Köse, Ahmet Arda Atalik

The conditional mean is a fundamental and important quantity whose applications include the theories of estimation and rate-distortion. It is also notoriously difficult to work with. This paper establishes novel bounds on the differential entropy of the co ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

The Gray-Wyner Network and Wyner's Common Information for Gaussian Sources

Michael Christoph Gastpar, Erixhen Sula

This paper presents explicit solutions for two related non-convex information extremization problems due to Gray and Wyner in the Gaussian case. The first problem is the Gray-Wyner network subject to a sum-rate constraint on the two private links. Here, ou ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

The Price of Distributed: Rate Loss in the CEO Problem

Michael Christoph Gastpar, Alper Köse, Ahmet Arda Atalik

In the distributed remote (CEO) source coding problem, many separate encoders observe independently noisy copies of an underlying source. The rate loss is the difference between the rate required in this distributed setting and the rate that would be requi ...

2022

Lower-bounds on the Bayesian Risk in Estimation Procedures via f–Divergences

Michael Christoph Gastpar, Adrien Vandenbroucque, Amedeo Roberto Esposito

We consider the problem of parameter estimation in a Bayesian setting and propose a general lower-bound that includes part of the family of f-Divergences. The results are then applied to specific settings of interest and compared to other notable results i ...

2022

Finite Littlestone Dimension Implies Finite Information Complexity

Michael Christoph Gastpar, Aditya Pradeep, Ido Nachum

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

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

Shannon Bounds on Lossy Gray-Wyner Networks

Michael Christoph Gastpar, Erixhen Sula

The Gray-Wyner network subject to a fidelity criterion is studied. Upper and lower bounds for the trade-offs between the private sum-rate and the common rate are obtained for arbitrary sources subject to mean-squared error distortion. The bounds meet exact ...

2022

From Generalisation Error to Transportation-cost Inequalities and Back

Michael Christoph Gastpar, Amedeo Roberto Esposito

In this work, we connect the problem of bounding the expected generalisation error with transportation-cost inequalities. Exposing the underlying pattern behind both approaches we are able to generalise them and go beyond Kullback- Leibler Divergences/Mutu ...

2022

Graph Chatbot

Chattez avec Graph Search

Posez n’importe quelle question sur les cours, conférences, exercices, recherches, actualités, etc. de l’EPFL ou essayez les exemples de questions ci-dessous.

AVERTISSEMENT : Le chatbot Graph n'est pas programmé pour fournir des réponses explicites ou catégoriques à vos questions. Il transforme plutôt vos questions en demandes API qui sont distribuées aux différents services informatiques officiellement administrés par l'EPFL. Son but est uniquement de collecter et de recommander des références pertinentes à des contenus que vous pouvez explorer pour vous aider à répondre à vos questions.

Connectez-vous pour utiliser Chat avec Graph Search