中文
相关论文

相关论文: Lipschitz Robustness of Finite-state Transducers

200 篇论文

We present the first study of robustness of systems that are both timed as well as reactive (I/O). We study the behavior of such timed I/O systems in the presence of "uncertain inputs" and formalize their robustness using the analytic…

形式语言与自动机理论 · 计算机科学 2015-06-04 Thomas A. Henzinger , Jan Otop , Roopsha Samanta

Deep Networks have been shown to provide state-of-the-art performance in many machine learning challenges. Unfortunately, they are susceptible to various types of noise, including adversarial attacks and corrupted inputs. In this work we…

机器学习 · 计算机科学 2019-09-12 Carlos Lassance , Vincent Gripon , Jian Tang , Antonio Ortega

We consider input-deterministic finite state transducers with infinite inputs and infinite outputs, and we consider the property of Borel normality on infinite words. When these transducers are given by a strongly connected set of states,…

形式语言与自动机理论 · 计算机科学 2019-04-22 Olivier Carton , Elisa Orduna

Transductions are binary relations of finite words. For rational transductions, i.e., transductions defined by finite transducers, the inclusion, equivalence and sequential uniformisation problems are known to be undecidable. In this paper,…

形式语言与自动机理论 · 计算机科学 2016-03-01 Emmanuel Filiot , Ismaël Jecker , Christof Löding , Sarah Winter

A word-to-word function is rational if it can be realized by a non-deterministic one-way transducer. Over finite words, it is a classical result that any rational function is regular, i.e. it can be computed by a deterministic two-way…

形式语言与自动机理论 · 计算机科学 2022-11-04 Olivier Carton , Gaëtan Douéneau-Tabot

The question whether P equals NP revolves around the discrepancy between active production and mere verification by Turing machines. In this paper, we examine the analogous problem for finite transducers and automata. Every nondeterministic…

计算复杂性 · 计算机科学 2021-05-03 Elisabet Burjons , Fabian Frei , Martin Raszyk

A word-to-word function is continuous for a class of languages~$\mathcal{V}$ if its inverse maps $\mathcal{V}$_languages to~$\mathcal{V}$. This notion provides a basis for an algebraic study of transducers, and was integral to the…

形式语言与自动机理论 · 计算机科学 2023-06-22 Michaël Cadilhac , Olivier Carton , Charles Paperman

Designing neural networks with bounded Lipschitz constant is a promising way to obtain certifiably robust classifiers against adversarial examples. However, the relevant progress for the important $\ell_\infty$ perturbation setting is…

机器学习 · 计算机科学 2022-10-28 Bohang Zhang , Du Jiang , Di He , Liwei Wang

Finite (word) state transducers extend finite state automata by defining a binary relation over finite words, called rational relation. If the rational relation is the graph of a function, this function is said to be rational. The class of…

形式语言与自动机理论 · 计算机科学 2025-04-25 Emmanuel Filiot , Ismaël Jecker , Khushraj Madnani , Saina Sunny

Any two-way finite state automaton is equivalent to some one-way finite state automaton. This well-known result, shown by Rabin and Scott and independently by Shepherdson, states that two-way finite state automata (even non-deterministic)…

形式语言与自动机理论 · 计算机科学 2013-04-29 Emmanuel Filiot , Olivier Gauwin , Pierre-Alain Reynier , Frédéric Servais

Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small adversarial change of an originally with high confidence correctly classified input leads to a wrong classification again with high…

机器学习 · 计算机科学 2017-11-07 Matthias Hein , Maksym Andriushchenko

Regular functions of infinite words are (partial) functions realized by deterministic two-way transducers with infinite look-ahead. Equivalently, Alur et. al. have shown that they correspond to functions realized by deterministic Muller…

形式语言与自动机理论 · 计算机科学 2023-02-15 Olivier Carton , Gaëtan Douéneau-Tabot , Emmanuel Filiot , Sarah Winter

A generalized dynamical robust nonlinear filtering framework is established for a class of Lipschitz differential algebraic systems, in which the nonlinearities appear both in the state and measured output equations. The system is assumed…

系统与控制 · 计算机科学 2014-02-25 Masoud Abbaszadeh

Regular functions from infinite words to infinite words can be equivalently specified by MSO-transducers, streaming $\omega$-string transducers as well as deterministic two-way transducers with look-ahead. In their one-way restriction, the…

形式语言与自动机理论 · 计算机科学 2024-09-19 V. Dave , E. Filiot , S. Krishna , N. Lhote

Transducers generalise automata by producing output word(s) for each input word, thereby defining a relation over words. A transducer is said to be finite-valued if, for every input word, it produces at most $k$ output words, for some…

形式语言与自动机理论 · 计算机科学 2026-05-08 Prince Mathew , Saina Sunny

Stability and robustness are critical for deploying Transformers in safety-sensitive settings. A principled way to enforce such behavior is to constrain the model's Lipschitz constant. However, approximation-theoretic guarantees for…

机器学习 · 计算机科学 2026-02-18 Takashi Furuya , Davide Murari , Carola-Bibiane Schönlieb

Transducers extend finite state automata with outputs, and describe transformations from strings to strings. Sequential transducers, which have a deterministic behaviour regarding their input, are of particular interest. However, unlike…

计算机科学中的逻辑 · 计算机科学 2019-03-01 Pierre-Alain Reynier , Didier Villevalois

An iterated uniform finite-state transducer (IUFST) runs the same length-preserving transduction, starting with a sweep on the input string and then iteratively sweeping on the output of the previous sweep. The IUFST accepts the input…

形式语言与自动机理论 · 计算机科学 2023-06-22 Martin Kutrib , Andreas Malcher , Carlo Mereghetti , Beatrice Palano

Deterministic two-way transducers capture the class of regular functions. The efficiency of composing two-way transducers has a direct implication in algorithmic problems related to reactive synthesis, where transformation specifications…

形式语言与自动机理论 · 计算机科学 2024-07-01 Luc Dartois , Paul Gastin , Loïc Germerie Guizouarn , R. Govind , Shankaranarayanan Krishna

For a given stable recurrent neural network (RNN) that is trained to perform a classification task using sequential inputs, we quantify explicit robustness bounds as a function of trainable weight matrices. The sequential inputs can be…

机器学习 · 计算机科学 2022-03-11 Guangyi Liu , Arash Amini , Martin Takac , Nader Motee
‹ 上一页 1 2 3 10 下一页 ›