检索结果-内蒙古大学图书馆

probabilistic Compute-in-Memory Design for Efficient Markov Chain Monte Carlo Sampling

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2024年第2期71卷 703-716页

作者： Fu, Yihan Shi, Daijing Fan, Anjunyi Yue, Wenshuo Yang, Yuchao Huang, Ru Yan, Bonan Peking Univ Inst Artificial Intelligence Sch IntegratedCircuits Beijing 100871 Peoples R China Peking Univ Beijing Adv Innovat Ctr Integrated Circuits Sch Integrated Circuits Beijing 100871 Peoples R China Peking Univ Sch Elect & Comp Engn Shenzhen 518055 Peoples R China Chinese Inst Brain Res CIBR Beijing 102206 Peoples R China

Markov chain Monte Carlo (MCMC) is a widely used sampling method in modern artificial intelligence and probabilistic computing systems. It involves repetitive random number generations and thus often dominates the latency of probabilistic model computing. Hence, we propose a compute-in-memory (CIM) based MCMC design as a hardware acceleration solution. This work investigates SRAM bitcell stochasticity and proposes a novel "pseudo-read" operation, based on which we offer a block-wise random number generation circuit scheme for fast random number generation. Moreover, this work proposes a novel multi-stage exclusive-OR gate (MSXOR) design method to generate strictly uniformly distributed random numbers. The probability error deviating from a uniform distribution is suppressed under 10(-6) . Also, this work presents a novel in-memory copy circuit scheme to realize data copy inside a CIM sub-array, significantly reducing the use of R/W circuits for power saving. Evaluated in a commercial 28-nm process development kit, this CIM-based MCMC design generates 4-bit similar to 32-bit samples with an energy efficiency of 0.53 pJ/sample and high throughput of up to 1066.7M samples/s. Compared to conventional processors, the overall energy efficiency improves 2.12 x 10(9) to 9.58 x 10(9) times.

关键词： SRAM processing-in-memory Markov chain Monte Carlo sampling MCMC accelerator probabilistic programming random number generator arbitrary distribution

来源：评论

学校读者我要写书评

暂无评论

Bayesian analysis of the relationship between process improvement practices and procurement maturity

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2023年第1期181卷

作者： Coskun, Serdar Semih Kazan, Halim Istanbul Univ Fac Econ Dept Business Adm Cent Campus TR-34116 Istanbul Turkiye

Procurement maturity becomes a crucial indicator reflecting how effectively and efficiently a procurement function fulfills the expectations. Purchasing and supply management literature posits several maturity evalu-ation models providing tools for a comprehensive assessment of excellence. Quality management literature also handles that excellence issue from the process improvement perspective. This study investigates the role of process improvement practices in improving the maturity level of procurement organizations. A maturity assessment survey collects data from 96 purchasing and supply management professionals. We suggest a Bayesian hierarchical mean difference model that deploys a Markov Chain Monte Carlo (MCMC) sampler in inferring posterior parameters. Results indicate that firms regularly practicing process improvement activities have statistically higher performance than rarely or never practicing firms on aggregate procurement maturity and its sub-dimensions. These results emphasize that process improvement escalates procurement maturity from reactive to proactive level. As a novel branch of data science, we discuss the advantages of Bayesian hypothesis testing with the probabilistic programming approach compared to the traditional frequentist hypothesis testing.

关键词： Procurement maturity Process improvement practices Bayesian hierarchical models probabilistic programming Markov Chain Monte Carlo

来源：评论

学校读者我要写书评

暂无评论

Automatic Differentiation in Prolog

引用

THEORY AND PRACTICE OF LOGIC programming 2023年第4期23卷 900-917页

作者： Schrijvers, Tom Van Den Berg, Birthe Riguzzi, Fabrizio Katholieke Univ Leuven Leuven Belgium Univ Ferrara Ferrara Italy

Automatic differentiation (AD) is a range of algorithms to compute the numeric value of a function's (partial) derivative, where the function is typically given as a computer program or abstract syntax tree. AD has become immensely popular as part of many learning algorithms, notably for neural networks. This paper uses Prolog to systematically derive gradient-based forward- and reverse-mode AD variants from a simple executable specification: evaluation of the symbolic derivative. Along the way we demonstrate that several Prolog features (DCGs, co-routines) contribute to the succinct formulation of the algorithm. We also discuss two applications in probabilistic programming that are enabled by our Prolog algorithms. The first is parameter learning for the Sum-Product Loop Language and the second consists of both parameter learning and variational inference for probabilistic logic programming.

关键词： Prolog automatic differentiation probabilistic programming

来源：评论

学校读者我要写书评

暂无评论

Past, Present and Future of Software for Bayesian Inference

引用

STATISTICAL SCIENCE 2024年第1期39卷 46-61页

作者： Strumbelj, Erik Bouchard-Cote, Alexandre Corander, Jukka Gelman, Andrew Rue, Havard Murray, Lawrence Pesonen, Henri Plummer, Martyn Vehtari, Aki Univ Ljubljana Fac Comp & Informat Sci Ljubljana Slovenia Univ British Columbia Stat Vancouver BC Canada Univ Oslo Fac Med Oslo Norway Univ Helsinki Fac Sci Helsinki Finland Wellcome Sanger Inst Cambridge England Columbia Univ Stat & Polit Sci New York NY 10027 USA King Abdullah Univ Sci & Technol Stat Thuwal Saudi Arabia Oslo Univ Hosp Oslo Ctr Biostat & Epidemiol Oslo Norway Univ Warwick Stat Warwick England Aalto Univ Computat Bayesian Modeling Aalto Finland

Software tools for Bayesian inference have undergone rapid evolution in the past three decades, following popularisation of the first generation MCMC-sampler implementations. More recently, exponential growth in the number of users has been stimulated both by the active development of new packages by the machine learning community and popularity of specialist software for particular applications. This review aims to summarize the most popular software and provide a useful map for a reader to navigate the world of Bayesian computation. We anticipate a vigorous continued development of algorithms and corresponding software in multiple research fields, such as probabilistic programming, likelihood -free inference and Bayesian neural networks, which will further broaden the possibilities for employing the Bayesian paradigm in exciting applications.

关键词： Statistics data analysis MCMC computation probabilistic programming

来源：评论

学校读者我要写书评

暂无评论

ELVES Measurements in the "UV Atmosphere" (Mini-EUSO) Experiment Onboard the ISS and Their Reconstruction

引用

COSMIC RESEARCH 2024年第4期62卷 330-338页

作者： Sharakin, S. Barghini, D. Battisti, M. Belov, A. Bertaina, M. Bianciotto, M. Bisconti, F. Blaksley, C. Blin, S. Cambie, G. Capel, F. Casolino, M. Ebisuzaki, T. Eser, J. Fenu, F. Franceschi, M. A. Golzio, A. Gorodetsky, P. Kajino, F. Kasuga, H. Klimov, P. Manfrin, M. Marcelli, L. Marszal, W. Miyamoto, H. Mignone, M. Murashov, A. Napolitano, T. Ohmori, H. Olinto, A. Parizot, E. Picozza, P. Piotrowski, L. W. Plebaniak, Z. Prevot, G. Reali, E. Ricci, M. Romoli, G. Sakaki, N. Shinozaki, K. Szabelski, J. De la Taille, C. Takizawa, Y. Vrabel, M. Wiencke, L. Zotov, M. Moscow MV Lomonosov State Univ Skobeltsyn Inst Nucl Phys Moscow 119991 Russia INFN Sect Turin I-10125 Turin Italy Univ Turin Dept Phys I-10125 Turin Italy INAF Astrophys Observ Turin I-10025 Pino Torinese Italy Univ Paris Cite CNRS Astroparticule & Cosmol F-75013 Paris France Moscow MV Lomonosov State Univ Fac Phys Moscow 119991 Russia INFN Sect Rome Tor Vergata I-00133 Rome Italy RIKEN Wako 3510198 Japan Univ Roma Tor Vergata Dept Phys I-00133 Rome Italy Tech Univ Munich D-80333 Munich Germany Univ Chicago Dept Astron & Astrophys Chicago IL 60637 USA Agenzia Spaziale Italiana I-00133 Rome Italy INFN Natl Labs Frascati I-00044 Frascati Italy Konan Univ Dept Phys Kobe Hyogo 6588501 Japan Natl Ctr Nucl Res PL-05400 Otwock Poland Univ Warsaw Fac Phys Pasteura 5 PL-02093 Warsaw Poland Stefan Batory Acad Appl Sci PL-96100 Skierniewice Poland Ecole Polytech Omega CNRS IN2P3 Palaiseau I-91120 France Colorado Sch Mines Dept Phys Golden CO 80401 USA

More than three dozen submillisecond events of ELVES type ("elves"), which are the result of the interaction of the front of an electromagnetic pulse from a lightning discharge and the lower layer of the ionosphere, have been identified in the data of a UV Atmosphere orbital multichannel detector (Mini-EUSO). Each event has a characteristic annular glow pattern and occupies a significant part of the detector's field of view, and the signal in a separate channel has an asymmetric profile with a pronounced peak. The distribution of peak times contains information about both the localization of the discharge and the altitude of the glow. In this paper, we propose a Bayesian (probabilistic) model for reconstructing ELVES events, implemented using probabilistic programming methods in PyMC-5. The capabilities of the model for determining the position of the discharge are shown using the example of several events. Methods for modifying the model to restore the discharge orientation and refine the glow height are outlined.

关键词： UV atmosphere orbital detector transient atmospheric phenomena Bayesian inference probabilistic programming

来源：评论

学校读者我要写书评

暂无评论

Programmable MCMC with Soundly Composed Guide Programs

引用

PROCEEDINGS OF THE ACM ON programming LANGUAGES-PACMPL 2024年第OOPSLA期8卷 1051-1080页

作者： Pham, Long Wang, Di Saad, Feras A. Hoffmann, Jan Carnegie Mellon Univ Pittsburgh PA 15213 USA Peking Univ Beijing Peoples R China

probabilistic programming languages (PPLs) provide language support for expressing flexible probabilistic models and solving Bayesian inference problems. PPLs with programmable inference make it possible for users to obtain improved results by customizing inference engines using guide programs that are tailored to a corresponding model program. However, errors in guide programs can compromise the statistical soundness of the inference. This article introduces a novel coroutine-based framework for verifying the correctness of user-written guide programs for a broad class of Markov chain Monte Carlo (MCMC) inference algorithms. Our approach rests on a novel type system for describing communication protocols between a model program and a sequence of guides that each update only a subset of random variables. We prove that, by translating guide types to context-free processes with finite norms, it is possible to check structural type equality between models and guides in polynomial time. This connection gives rise to an efficient type-inference algorithm for probabilistic programs with flexible constructs such as general recursion and branching. We also contribute a coverage-checking algorithm that verifies the support of sequentially composed guide programs agrees with that of the model program, which is a key soundness condition for MCMC inference with multiple guides. Evaluations on diverse benchmarks show that our type-inference and coverage-checking algorithms efficiently infer types and detect sound and unsound guides for programs that existing static analyses cannot handle.

关键词： probabilistic programming Bayesian inference type systems coroutines context-free types

来源：评论

学校读者我要写书评

暂无评论

Program equivalence in a typed probabilistic call-by-need functional language

引用

JOURNAL OF LOGICAL AND ALGEBRAIC METHODS IN programming 2023年 135卷

作者： Schmidt-Schauss, Manfred Sabel, David Goethe Univ Frankfurt Main Frankfurt Germany

We extend a call-by-need variant of PCF with a binary probabilistic fair choice operator, which makes a lazy and typed variant of probabilistic functional programming. We define a contextual equivalence that respects the expected convergence of expressions and prove a corresponding context lemma. This enables us to show correctness of several program transformations with respect to contextual equivalence. Distribution -equivalence of expressions of numeric type is introduced. While the notion of contextual equivalence stems from program semantics, the notion of distribution equivalence is a direct description of the stochastic model. Our main result is that both notions are compatible: We show that for closed expressions of numeric type contextual equivalence and distribution-equivalence coincide. This provides a strong and often operationally feasible criterion for contextual equivalence of expressions and programs.(c) 2023 Elsevier Inc. All rights reserved.

关键词： probabilistic programming Lambda-calculus Semantics Call-by-need evaluation Program transformations

来源：评论

学校读者我要写书评

暂无评论

Mixed Nondeterministic-probabilistic Automata

引用

DISCRETE EVENT DYNAMIC SYSTEMS-THEORY AND APPLICATIONS 2023年第4期33卷 455-505页

作者： Benveniste, Albert Raclet, Jean-Baptiste Inria Rennes Bretagne Atlantique F-35042 Rennes France Univ Toulouse IRIT CNRS Toulouse INPUT3 Toulouse France

Graphical models in probability and statistics are a core concept in the area of probabilistic reasoning and probabilistic programming-graphical models include Bayesian networks and factor graphs. For modeling and formal verification of probabilistic systems, probabilistic automata were introduced. This paper proposes a coherent suite of models consisting of Mixed Systems, Mixed Bayesian Networks, and Mixed Automata, which extend factor graphs, Bayesian networks, and probabilistic automata with the handling of nondeterminism. Each of these models comes with a parallel composition, and we establish clear relations between these three models. Also, we provide a detailed comparison between Mixed Automata and probabilistic Automata

关键词： probabilistic automata Semantics Nondeterminism and probability Factor graphs Bayesian networks probabilistic programming

来源：评论

学校读者我要写书评

暂无评论

Direct Bayesian inference for fault severity assessment in Digital-Twin-Based fault diagnosis

引用

ANNALS OF NUCLEAR ENERGY 2023年第1期194卷

作者： Nguyen, Tat Nghia Vilim, Richard B. Argonne Natl Lab Nucl Sci & Engn Div Lemont IL 60439 USA

For applications in condition-based maintenance of nuclear systems, the assessment of fault severity is crucial. In this work, we developed a framework that allows for direct inference of the probability distributions of possible faults in a system. We employed a model-based approach with model residuals generated from analytical redundancy relations provided by physics-based models of the system components. From real-time sensor readings, the values of the model residuals can be calculated, and the posterior probability distributions of the faults can be computed directly using the methods of Bayesian networks. From the posterior distribution of each fault, one can estimate the fault probability based on a chosen threshold and assess the severity of the fault. By eliminating the discretization and simplifications in middle steps, this approach allows us to leverage the available computational resources to provide more accurate fault probability estimates and severity assessments.

关键词： Model-based diagnosis Fault detection Bayesian inference probabilistic programming Digital twin

来源：评论

学校读者我要写书评

暂无评论

Mastering uncertainty in performance estimations of configurable software systems

引用

EMPIRICAL SOFTWARE ENGINEERING 2023年第2期28卷 1-40页

作者： Dorn, Johannes Apel, Sven Siegmund, Norbert Univ Leipzig D-04109 Leipzig Germany Saarland Univ D-60041 Saarbrucken Germany Saarland Informat Campus D-60041 Saarbrucken Germany

Understanding the influence of configuration options on the performance of a software system is key for finding optimal system configurations, system understanding, and performance debugging. In the literature, a number of performance-influence modeling approaches have been proposed, which model a configuration option's influence and a configuration's performance as a scalar value. However, these point estimates falsely imply a certainty regarding an option's influence that neglects several sources of uncertainty within the assessment process, such as (1) measurement bias, choices of model representation and learning process, and incomplete data. This leads to the situation that different approaches and even different learning runs assign different scalar performance values to options and interactions among them. The true influence is uncertain, though. There is no way to quantify this uncertainty with state-of-the-art performance modeling *** propose a novel approach, P4, which is based on probabilistic programming, that explicitly models uncertainty for option influences and consequently provides a confidence interval for each prediction alongside a scalar. This way, we can explain, for the first time, why predictions may be erroneous and which option's influence may be unreliable. An evaluation on 13 real-world subject systems shows that P4's accuracy is in line with the state of the art while providing reliable confidence intervals, in addition to scalar predictions. We qualitatively explain how uncertain influences of individual options and interactions cause inaccurate predictions.

关键词： probabilistic programming Performance-influence modeling Configurable software systems Bayesian inference P4

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：