English
Related papers

Related papers: Dp-rank and forbidden configurations

200 papers

An information-theoretic framework is introduced to analyze last-layer embedding, focusing on learned representations for regression tasks. We define representation-rate and derive limits on the reliability with which input-output…

Information Theory · Computer Science 2026-05-27 Deborah Pereg , Michael Wand

In a previous paper we have presented a CEGAR approach for the verification of parameterized systems with an arbitrary number of processes organized in an array or a ring. The technique is based on the iterative computation of parameterized…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-09-21 Javier Esparza , Mikhail Raskin , Christoph Welzel

The rank of neural networks measures information flowing across layers. It is an instance of a key structural condition that applies across broad domains of machine learning. In particular, the assumption of low-rank feature representations…

Machine Learning · Computer Science 2022-06-14 Ruili Feng , Kecheng Zheng , Yukun Huang , Deli Zhao , Michael Jordan , Zheng-Jun Zha

We extend the notion of a strong backdoor from the CSP setting to the Valued CSP setting (VCSP, for short). This provides a means for augmenting a class of tractable VCSP instances to instances that are outside the class but of small…

Data Structures and Algorithms · Computer Science 2016-12-20 Robert Ganian , M. S. Ramanujan , Stefan Szeider

Unobserved discrete data are ubiquitous in many scientific disciplines, and how to learn the causal structure of these latent variables is crucial for uncovering data patterns. Most studies focus on the linear latent variable model or…

Machine Learning · Computer Science 2024-06-12 Zhengming Chen , Ruichu Cai , Feng Xie , Jie Qiao , Anpeng Wu , Zijian Li , Zhifeng Hao , Kun Zhang

In the paper a new sufficient condition for the Aubin property to a class of parameterized variational systems is derived. In these systems the constraints depend both on the parameter as well as on the decision variable itself and they…

Optimization and Control · Mathematics 2018-10-31 Helmut Gfrerer , Jiri V. Outrata

This paper presents an information theory based detection framework for covert channels. We first show that the usual notion of interference does not characterize the notion of deliberate information flow of covert channels. We then show…

Cryptography and Security · Computer Science 2011-03-01 Loïc Hélouët , Aline Roumy

A phenomenological paradigm for the study of CPT-violating effects in the neutral kaon system is presented. Besides the familiar direct and indirect breakings, it encodes possible phenomena leading to irreversibility and dissipation, that…

High Energy Physics - Phenomenology · Physics 2007-05-23 F. Benatti , R. Floreanini

Contextual multi-armed bandits (CMAB) have been widely used for learning to filter and prioritize information according to a user's interest. In this work, we analyze top-K ranking under the CMAB framework where the top-K arms are chosen…

Machine Learning · Computer Science 2022-01-31 Michael Rawson , Jade Freeman

We propose an extensible deep learning method that uses reinforcement learning to train neural networks for offline ranking in information retrieval (IR). We call our method BanditRank as it treats ranking as a contextual bandit problem. In…

Information Retrieval · Computer Science 2019-10-24 Phanideep Gampa , Sumio Fujita

We present a framework to derive risk bounds for vector-valued learning with a broad class of feature maps and loss functions. Multi-task learning and one-vs-all multi-category learning are treated as examples. We discuss in detail…

Machine Learning · Statistics 2016-06-07 Andreas Maurer , Massimiliano Pontil

The main result of this article is sub-additivity of the dp-rank. We also show that the study of theories of finite dp-rank can not be reduced to the study of its dp-minimal types, and discuss the possible relations between dp-rank and…

Logic · Mathematics 2011-12-30 Itay Kaplan , Alf Onshuus , Alexander Usvyatsov

Learning-based control aims to construct models of a system to use for planning or trajectory optimization, e.g. in model-based reinforcement learning. In order to obtain guarantees of safety in this context, uncertainty must be accurately…

Robotics · Computer Science 2020-06-08 David D. Fan , Ali-akbar Agha-mohammadi , Evangelos A. Theodorou

The statistical censoring setup is extended to the situation when random measures can be assigned to the realization of datapoints, leading to a new way of incorporating expert information into the usual parametric estimation procedures.…

Methodology · Statistics 2023-12-05 Hansjörg Albrecher , Martin Bladt

Knowledge tracing consists in predicting the performance of some students on new questions given their performance on previous questions, and can be a prior step to optimizing assessment and learning. Deep knowledge tracing (DKT) is a…

Computers and Society · Computer Science 2023-12-27 Jill-Jênn Vie , Hisashi Kashima

Consider an experiment involving a potentially small number of subjects. Some random variables are observed on each subject: a high-dimensional one called the "observed" random variable, and a one-dimensional one called the "outcome" random…

Machine Learning · Statistics 2018-06-15 Tarun Yellamraju , Mireille Boutin

We consider deep multivariate models for heterogeneous collections of random variables. In the context of computer vision, such collections may e.g. consist of images, segmentations, image attributes, and latent variables. When developing…

Machine Learning · Computer Science 2026-02-03 Dmitrij Schlesinger , Boris Flach , Alexander Shekhovtsov

Inverse Constraint Learning (ICL) is the problem of inferring constraints from safe (i.e., constraint-satisfying) demonstrations. The hope is that these inferred constraints can then be used downstream to search for safe policies for new…

Robotics · Computer Science 2025-08-05 Mohamad Qadri , Gokul Swamy , Jonathan Francis , Michael Kaess , Andrea Bajcsy

This paper concerns matrix decompositions in which the factors are restricted to lie in a closed subvariety of a matrix group. Such decompositions are of relevance in control theory: given a target matrix in the group, can it be decomposed…

Algebraic Geometry · Mathematics 2020-05-29 Jan Draisma

Mathematically characterizing the implicit regularization induced by gradient-based optimization is a longstanding pursuit in the theory of deep learning. A widespread hope is that a characterization based on minimization of norms may…

Machine Learning · Computer Science 2020-10-20 Noam Razin , Nadav Cohen