activity
20102026
most citedOn the Number of Linear Regions of Deep Neural Networks

832 citations · 1.3k across the 79 of their papers we have counts for

collaborators
Showing cs.ITShow all

6 papers · 1 filter

cs.IT2022

Continuity and Additivity Properties of Information Decompositions

Johannes Rauh, Pradeep Kr. Banerjee, Eckehard Olbrich +2

Information decompositions quantify how the Shannon information about a given random variable is distributed among several other random variables. Various requirements have been pr…

cs.IT2019

Factorized Mutual Information Maximization

Thomas Merkh, Guido Montúfar

We investigate the sets of joint probability distributions that maximize the average multi-information over a collection of margins. These functionals serve as proxies for maximizi…

cs.IT2018★ 4 cited

The Variational Deficiency Bottleneck

Pradeep Kr. Banerjee, Guido Montúfar

We introduce a bottleneck method for learning data representations based on information deficiency, rather than the more traditional information sufficiency. A variational upper bo…

cs.IT2017★ 18 cited

Computing the Unique Information

Pradeep Kr. Banerjee, Johannes Rauh, Guido Montúfar

Given a pair of predictor variables and a response variable, how much information do the predictors have about the response, and how is this information distributed between unique,…

cs.IT2014

Sequential Recurrence-Based Multidimensional Universal Source Coding of Lempel-Ziv Type

Tyll Krueger, Guido Montufar, Ruedi Seiler +1

We define an algorithm that parses multidimensional arrays sequentially into mainly unrepeated but nested multidimensional sub-arrays of increasing size, and show that the resultin…

cs.IT2011★ 1 cited

Universally Typical Sets for Ergodic Sources of Multidimensional Data

Tyll Krueger, Guido Montufar, Ruedi Seiler +1

We lift important results about universally typical sets, typically sampled sets, and empirical entropy estimation in the theory of samplings of discrete ergodic information source…