activity
20102026
most citedEstimation Efficiency Under Privacy Constraints

69 citations · 176 across the 37 of their papers we have counts for

collaborators

48 papers

cs.IT2026

Variable Rate Lossy Source-Channel Coding over Channels with Feedback

Timothy Liu, Fady Alajaji, Tamás Linder

A variable-rate lossy joint source-channel coding scheme for burst-noise communication channels with noiseless feedback is introduced. The scheme comprises a multi-stage channel op…

cs.IT2023

Lossless Transformations and Excess Risk Bounds in Statistical Inference

László Györfi, Tamás Linder, Harro Walk

We study the excess minimum risk in statistical inference, defined as the difference between the minimum expected loss in estimating a random variable from an observed feature vect…

math.OC2022

Logarithmic Regret in Adaptive Control of Noisy Linear Quadratic Regulator Systems Using Hints

Mohammad Akbari, Bahman Gharesifard, Tamas Linder

The problem of regret minimization for online adaptive control of linear-quadratic systems is studied. In this problem, the true system transition parameters (matrices and )…

cs.IT2022★ 3 cited

Rényi Cross-Entropy Measures for Common Distributions and Processes with Memory

Ferenc Cole Thierrin, Fady Alajaji, Tamás Linder

Two Rényi-type generalizations of the Shannon cross-entropy, the Rényi cross-entropy and the Natural Rényi cross-entropy, were recently used as loss functions for the improved desi…

cs.IT2022

On the Rényi Cross-Entropy

Ferenc Cole Thierrin, Fady Alajaji, Tamás Linder

The Rényi cross-entropy measure between two distributions, a generalization of the Shannon cross-entropy, was recently used as a loss function for the improved design of deep learn…

math.OC2022

An Asymptotically Optimal Two-Part Fixed-Rate Coding Scheme for Networked Control with Unbounded Noise

Jonathan Keeler, Tamás Linder, Serdar Yüksel

It is known that under fixed-rate information constraints, adaptive quantizers can be used to stabilize an open-loop-unstable linear system on driven by unbounded no…