Jürgen Forster

dblp:55/5267 · DBLP profile ↗
← Back
12ranked-venue papers
11as first author
0since 2021 · last 2006
—ORCID · none

Domains — the database's venue-derived domains; a paper can count in several

Artificial intelligence and machine learning · 6 · 5 first-authorTheory of computation · 6 · 6 first-author

Expertise — from the expertise taxonomy: the topics of the expert's papers under the CCF categories. A weight counts papers with recency: 1 for a paper about the topic, 0.3 when the topic is its context, halved every five years.

Artificial intelligence
2 papers
Learning theory · 67% Reinforcement learning · 33%
Theoretical computer science
1 paper
Computational complexity · 100%

Topics — the 5 heaviest of 5, each with the papers that count most for it

TopicWeightPapersLastEvidence papers
Computational complexity
communication complexity
0.012001
A Linear Lower Bound on the Unbounded Error Probabilistic Communication Complexity · CCC 2001
Computational complexity
randomized computation
0.012001
A Linear Lower Bound on the Unbounded Error Probabilistic Communication Complexity · CCC 2001
Machine learning › Learning theory › learning bounds
loss bounds
0.012000
Relative Expected Instantaneous Loss Bounds · COLT 2000
Machine learning › Learning theory › online learning
regret bounds
0.012000
Relative Loss Bounds for Temporal-Difference Learning · ICML 2000
Machine learning › Reinforcement learning
temporal difference learning
0.012000
Relative Loss Bounds for Temporal-Difference Learning · ICML 2000

Methods — techniques the papers use, named apart from their topics

margin bounds · 0.0half-space embedding · 0.0hadamard matrix · 0.0
YearPublicationVenuePosition
2006 On the smallest possible dimension and the largest possible margin of linear arrangements representing given concept classes
Jürgen Forster, Hans Simon 0001
Theor. Comput. Sci.1
2003 Estimating the Optimal Margins of Embeddings in Euclidean Half Spaces
Jürgen Forster, Niels Schmitt, Hans Simon 0001, Thorsten Suttorp
Mach. Learn.1
2003 Relative Loss Bounds for Temporal-Difference Learning
Jürgen Forster, Manfred K. Warmuth
Mach. Learn.1
2002 How to Achieve Minimax Expected Kullback-Leibler Distance from an Unknown Finite Distribution
Dietrich Braess, Jürgen Forster, Tomas Sauer, Hans Simon 0001
ALT2
2002 On the Smallest Possible Dimension and the Largest Possible Margin of Linear Arrangements Representing Given Concept Classes Uniform Distribution
Jürgen Forster, Hans Simon 0001
ALT1
2002 A linear lower bound on the unbounded error probabilistic communication complexity
Jürgen Forster
J. Comput. Syst. Sci.1
2002 Relative Expected Instantaneous Loss Bounds
Jürgen Forster, Manfred K. Warmuth
J. Comput. Syst. Sci.1
2001 A Linear Lower Bound on the Unbounded Error Probabilistic Communication Complexity
abstract
We prove a general lower bound on the complexity of unbounded error probabilistic communication protocols. This result improves on a lower bound for bounded error protocols from Krause (1996). As a simple consequence we get the, to our knowledge, first linear lower bound on the complexity of unbounded error probabilistic communication protocols for the functions defined by Hadamard matrices. We also give an upper bound on the margin of any embedding of a concept class in half spaces.
Jürgen Forster
CCC1
2001 Relations Between Communication Complexity, Linear Arrangements, and Computational Complexity
Jürgen Forster, Matthias Krause 0001, Satyanarayana V. Lokam, Rustam Mubarakzjanov, Niels Schmitt, Hans Simon 0001
FSTTCS1
2000 Relative Expected Instantaneous Loss Bounds
Jürgen Forster, Manfred K. Warmuth
COLT1
2000 Relative Loss Bounds for Temporal-Difference Learning
Jürgen Forster, Manfred K. Warmuth
ICML1
1999 On Relative Loss Bounds in Generalized Linear Regression
Jürgen Forster
FCT1