English
Related papers

Related papers: Connecting Knowledge Compilation Classes and Width…

200 papers

Boolean circuits in d-DNNF form enable tractable probabilistic inference. However, as a key insight of this work, we show that commonly used d-DNNF compilation approaches introduce irrelevant subcircuits. We call these subcircuits Tseitin…

Artificial Intelligence · Computer Science 2024-07-26 Vincent Derkinderen

Message passing neural networks (MPNNs) are powerful models for node classification but suffer from performance limitations under heterophily (low same-class connectivity) and structural bottlenecks in the graph. We provide a unifying…

Machine Learning · Computer Science 2025-08-26 Jonathan Rubin , Sahil Loomba , Nick S. Jones

The use of Deep Learning hardware algorithms for embedded applications is characterized by challenges such as constraints on device power consumption, availability of labeled data, and limited internet bandwidth for frequent training on…

Machine Learning · Computer Science 2021-02-02 Siqiao Ruan , Ian Colbert , Ken Kreutz-Delgado , Srinjoy Das

We introduce a one-sided incidence tree decomposition of a CNF $\varphi$. This is a tree decomposition of the incidence graph of $\varphi$ where the underlying tree is rooted and the set of bags containing each clause induces a directed…

Computational Complexity · Computer Science 2022-09-01 Andrea Cali , Igor Razgon

Satisfiability of Boolean circuits is among the most known and important problems in theoretical computer science. This problem is NP-complete in general but becomes polynomial time when restricted either to monotone gates or linear gates.…

Computational Complexity · Computer Science 2017-10-24 Paweł M. Idziak , Jacek Krzaczkowski

Uncertainty quantification is essential in safety-critical settings--from autonomous driving to aviation, finance, and health--where decisions must rely on conservative bounds rather than point estimates. Predictor-level intervals (e.g.,…

Machine Learning · Computer Science 2026-05-18 Ruirui Liu , Xuejie Hou , Yiping Jiang , Hui Ren

Cardinality constraints or, more generally, weight constraints are well recognized as an important extension of answer-set programming. Clearly, all common algorithmic tasks related to programs with cardinality or weight constraints - like…

Logic in Computer Science · Computer Science 2020-02-19 Reinhard Pichler , Stefan Rümmele , Stefan Szeider , Stefan Woltran

We propose Trusted Neural Network (TNN) models, which are deep neural network models that satisfy safety constraints critical to the application domain. We investigate different mechanisms for incorporating rule-based knowledge in the form…

Machine Learning · Computer Science 2018-05-21 Shalini Ghosh , Amaury Mercier , Dheeraj Pichapati , Susmit Jha , Vinod Yegneswaran , Patrick Lincoln

The use of Shap scores has become widespread in Explainable AI. However, their computation is in general intractable, in particular when done with a black-box classifier, such as neural network. Recent research has unveiled classes of…

Artificial Intelligence · Computer Science 2023-07-25 Leopoldo Bertossi , Jorge E. Leon

Deep Neural Networks (DNNs) are widely used for their ability to effectively approximate large classes of functions. This flexibility, however, makes the strict enforcement of constraints on DNNs an open problem. Here we present a framework…

Machine Learning · Computer Science 2023-02-10 Eric Marcus , Ray Sheombarsing , Jan-Jakob Sonke , Jonas Teuwen

The reachability problem in multi-pushdown automata (MPDA) has many applications in static analysis of recursive programs. An example is safety verification of multi-threaded recursive programs with shared memory. Since these problems are…

Formal Languages and Automata Theory · Computer Science 2025-12-05 C. Aiswarya , Pascal Baumann , Prakash Saivasan , Lia Schütze , Georg Zetzsche

We consider the memorization capabilities of multilayered \emph{sign} perceptrons neural networks (SPNNs). A recent rigorous upper-bounding capacity characterization, obtained in \cite{Stojnictcmspnncaprdt23} utilizing the Random Duality…

Machine Learning · Statistics 2023-12-14 Mihailo Stojnic

Deep learning based methods hold state-of-the-art results in image denoising, but remain difficult to interpret due to their construction from poorly understood building blocks such as batch-normalization, residual learning, and feature…

Image and Video Processing · Electrical Eng. & Systems 2021-03-09 Nikola Janjušević , Amirhossein Khalilian-Gourtani , Yao Wang

In this article we present a protocol for building dense numeration in network with unknown topology. Additionally to a unique number each node as result of the protocol will get information about a spanning tree. This spanning tree is…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-04-03 Khuziev Ilnur

We propose a novel way to incorporate expert knowledge into the training of deep neural networks. Many approaches encode domain constraints directly into the network architecture, requiring non-trivial or domain-specific engineering. In…

Machine Learning · Computer Science 2021-11-03 Nicholas Hoernle , Rafael Michael Karampatsis , Vaishak Belle , Kobi Gal

Continuous-time Bayesian Networks (CTBNs) represent a compact yet powerful framework for understanding multivariate time-series data. Given complete data, parameters and structure can be estimated efficiently in closed-form. However, if…

Machine Learning · Statistics 2019-11-04 Dominik Linzner , Michael Schmidt , Heinz Koeppl

We study connectivity problems from a fine-grained parameterized perspective. Cygan et al. (TALG 2022) obtained algorithms with single-exponential running time $\alpha^{tw} n^{O(1)}$ for connectivity problems parameterized by treewidth…

Data Structures and Algorithms · Computer Science 2023-03-01 Falko Hegerfeld , Stefan Kratsch

We show that deep neural networks (DNNs) can efficiently learn any composition of functions with bounded $F_{1}$-norm, which allows DNNs to break the curse of dimensionality in ways that shallow networks cannot. More specifically, we derive…

Machine Learning · Statistics 2025-03-07 Arthur Jacot , Seok Hoan Choi , Yuxiao Wen

What kinds of functions are learnable from their satisfying assignments? Motivated by this simple question, we extend the framework of De, Diakonikolas, and Servedio [DDS15], which studied the learnability of probability distributions over…

Data Structures and Algorithms · Computer Science 2019-07-04 Clément L. Canonne , Anindya De , Rocco A. Servedio

The embedding and extraction of useful knowledge is a recent trend in machine learning applications, e.g., to supplement existing datasets that are small. Whilst, as the increasing use of machine learning models in security-critical…

Cryptography and Security · Computer Science 2021-10-27 Wei Huang , Xingyu Zhao , Xiaowei Huang