Zobrazeno 1 - 10
of 183
pro vyhledávání: '"Urbanke, Rüdiger"'
Autor:
Ivanov, Kirill, Urbanke, Rüdiger
Polar coding solutions demonstrate excellent performance under the list decoding that is challenging to implement in hardware due to the path sorting operations. As a potential solution to this problem, permutation decoding recently became a hot rese
Externí odkaz:
http://arxiv.org/abs/2112.12495
Modern machine learning systems have been applied successfully to a variety of tasks in recent years but making such systems robust against adversarially chosen modifications of input instances seems to be a much harder problem. It is probably fair t
Externí odkaz:
http://arxiv.org/abs/2112.09625
Autor:
Ivanov, Kirill, Urbanke, Rüdiger
The recently introduced polar codes constitute a breakthrough in coding theory due to their capacityachieving property. This goes hand in hand with a quasilinear construction, encoding, and successive cancellation list decoding procedures based on th
Externí odkaz:
http://arxiv.org/abs/2104.06084
Autor:
Głuch, Grzegorz, Urbanke, Rüdiger
Symmetries have proven to be important ingredients in the analysis of neural networks. So far their use has mostly been implicit or seemingly coincidental. We undertake a systematic study of the role that symmetry plays. In particular, we clarify how
Externí odkaz:
http://arxiv.org/abs/2104.05508
Autor:
Głuch, Grzegorz, Urbanke, Rüdiger
We prove an exponential separation for the sample complexity between the standard PAC-learning model and a version of the Equivalence-Query-learning model. We then show that this separation has interesting implications for adversarial robustness. We
Externí odkaz:
http://arxiv.org/abs/2102.05475
Autor:
Ivanov, Kirill, Urbanke, Rüdiger L.
Recently it was proved that if a linear code is invariant under the action of a doubly transitive permutation group, it achieves the capacity of erasure channel. Therefore, it is of sufficient interest to classify all codes, invariant under such perm
Externí odkaz:
http://arxiv.org/abs/2010.15453
Autor:
Głuch, Grzegorz, Urbanke, Rüdiger
There are two main attack models considered in the adversarial robustness literature: black-box and white-box. We consider these threat models as two ends of a fine-grained spectrum, indexed by the number of queries the adversary can ask. Using this
Externí odkaz:
http://arxiv.org/abs/2010.01039
Autor:
Liu, Wei, Urbanke, Rüdiger
We study the stability of low-density parity-check (LDPC) codes under blockwise or bitwise maximum $\textit{a posteriori}$ (MAP) decoding, where transmission takes place over a binary-input memoryless output-symmetric channel. Our study stems from th
Externí odkaz:
http://arxiv.org/abs/2009.08640
Autor:
Ivanov, Kirill, Urbanke, Rüdiger
A framework of monomial codes is considered, which includes linear codes generated by the evaluation of certain monomials. Polar and Reed-Muller codes are the two best-known representatives of such codes and can be considered as two extreme cases. Re
Externí odkaz:
http://arxiv.org/abs/2001.03790
Autor:
Głuch, Grzegorz, Urbanke, Rüdiger
Modern machine learning models with very high accuracy have been shown to be vulnerable to small, adversarially chosen perturbations of the input. Given black-box access to a high-accuracy classifier $f$, we show how to construct a new classifier $g$
Externí odkaz:
http://arxiv.org/abs/1912.07561