检索结果-内蒙古大学图书馆

simulation-based inference of single-molecule force spectroscopy

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2023年第2期4卷 025009页

作者： Dingeldein, Lars Cossio, Pilar Covino, Roberto Frankfurt Inst Adv Studies D-60438 Frankfurt Germany Goethe Univ Frankfurt Dept Phys D-60438 Frankfurt Germany Flatiron Inst Ctr Computat Math New York NY 10010 USA Flatiron Inst Ctr Computat Biol New York NY 10010 USA Int Max Planck Res Sch Cellular Biophys D-60438 Frankfurt Germany

Single-molecule force spectroscopy (smFS) is a powerful approach to studying molecular self-organization. However, the coupling of the molecule with the ever-present experimental device introduces artifacts, that complicate the interpretation of these experiments. Performing statistical inference to learn hidden molecular properties is challenging because these measurements produce non-Markovian time series, and even minimal models lead to intractable likelihoods. To overcome these challenges, we developed a computational framework built on novel statistical methods called simulation-based inference (SBI). SBI enabled us to directly estimate the Bayesian posterior, and extract reduced quantitative models from smFS, by encoding a mechanistic model into a simulator in combination with probabilistic deep learning. Using synthetic data, we could systematically disentangle the measurement of hidden molecular properties from experimental artifacts. The integration of physical models with machine-learning density estimation is general, transparent, easy to use, and broadly applicable to other types of biophysical experiments.

关键词： simulation-based inference likelihood-free derivative-free neural posterior estimation single-molecule biophysics force spectroscopy

来源：评论

学校读者我要写书评

暂无评论

Reversible Gromov--Monge Sampler for simulation-based inference\ast

引用

SIAM JOURNAL ON MATHEMATICS OF DATA SCIENCE 2024年第2期6卷 283-310页

作者： Hur, Yoonhaeng Guo, Wenxuan Liang, Tengyuan Univ Chicago Dept Stat Chicago IL 60637 USA Univ Chicago Booth Sch Business Chicago IL 60637 USA

This paper introduces a new simulation -based inference procedure to model and sample from multidimensional probability distributions given access to independent and identically distributed samples, circumventing the usual approaches of explicitly modeling the density function or designing Markov chain Monte Carlo. Motivated by the seminal work on distance and isomorphism between metric measure spaces, we develop a new transform sampler to perform simulation -based inference, which estimates a notion of optimal alignments between two heterogeneous metric measure spaces (\scrX, \mu , c\scrX) and (\scrY, \nu , c\scrY) from empirical data sets, with estimated maps that approximately push forward one measure \mu to the other \nu , and vice versa. We introduce a new notion called the reversible Gromov--Monge (RGM) distance, providing mathematical formalism behind the new sampler. We study the statistical rate of convergence of the new transform sampler, along with several analytic properties of the RGM distance and operator viewpoints of transform sampling. Synthetic and real -world examples showcasing the effectiveness of the new sampler are also demonstrated.

关键词： Gromov-Wasserstein metric transform sampling simulation-based inference generative models isomorphism likelihood-free inference

来源：评论

学校读者我要写书评

暂无评论

Accelerating simulation-based inference with Emerging AI Hardware

Accelerating Simulation-based Inference with Emerging AI Har...

引用

IEEE International Conference on Rebooting Computing (ICRC)

作者： Kulkarni, Sourabh Tsyplikhin, Alexander Krell, Mario Michael Moritz, Csaba Andras Univ Massachusetts Elect & Comp Engn Amherst MA 01003 USA Graphcore Palo Alto CA USA

ISBN: (纸本)9780738143378

Developing models of natural phenomena by capturing their underlying complex interactions is a core tenet of various scientific disciplines. These models are useful as simulators and can help in understanding the natural processes being studied. One key challenge in this pursuit has been to enable statistical inference over these models, which would allow these simulation-based models to learn from real-world observations. Recent efforts, such as Approximate Bayesian Computation (ABC), show promise in performing a new kind of inference to leverage these models. While the scope of applicability of these inference algorithms is limited by the capabilities of contemporary computational hardware, they show potential of being greatly parallelized. In this work, we explore hardware accelerated simulation-based inference over probabilistic models, by combining massively parallelized ABC inference algorithm with the cutting-edge AI chip solutions that are uniquely suited for this purpose. As a proof-of-concept, we demonstrate inference over a probabilistic epidemiology model used to predict the spread of COVID-19. Two hardware acceleration platforms are compared - the Tesla V100 GPU and the Graphcore Mark1 IPU. Our results show that while both of these platforms outperform multi-core CPUs, the Mk1 IPUs are 7.5x faster than the Tesla V100 GPUs for this workload.

关键词： Approximate Bayesian Computation COVID-19 epidemiology hardware acceleration high performance computing likelihood-free inference simulation-based inference

来源：评论

学校读者我要写书评

暂无评论

simulation-based inference of differentiation trajectories from RNA velocity fields

引用

CELL REPORTS METHODS 2022年第12期2卷 100359页

作者： Gupta, Revant Cerletti, Dario Gut, Gilles Oxenius, Annette Claassen, Manfred Univ Tubingen Univ Hosp Tubingen Fac Med Internal Med 1 Tubingen Germany Univ Tubingen Dept Comp Sci Tubingen Germany Swiss Fed Inst Technol Inst Mol Syst Biol Zurich Switzerland Swiss Fed Inst Technol Inst Microbiol Zurich Switzerland

We report Cytopath, a method for trajectory inference that takes advantage of transcriptional activity infor-mation from the RNA velocity of single cells to perform trajectory inference. Cytopath performs this task by defining a Markov chain model, simulating an ensemble of possible differentiation trajectories, and con-structing a consensus trajectory. We show that Cytopath can recapitulate the topological and molecular characteristics of the differentiation process under study. In our analysis, we include differentiation trajec-tories with varying bifurcated, circular, convergent, and mixed topologies studied in single-snapshot as well as time-series single-cell RNA sequencing experiments. We demonstrate the capability to reconstruct differentiation trajectories, assess the association of RNA velocity-based pseudotime with actually elapsed process time, and identify drawbacks in current state-of-the art trajectory inference approaches.

关键词： single-cell RNA sequencing RNA velocity trajectory inference simulation-based inference

来源：评论

学校读者我要写书评

暂无评论

simulation-based inference for model parameterization on analog neuromorphic hardware

引用

NEUROMORPHIC COMPUTING AND ENGINEERING 2023年第4期3卷 044006-044006页

作者： Kaiser, Jakob Stock, Raphael Mueller, Eric Schemmel, Johannes Schmitt, Sebastian Heidelberg Univ Kirchhoff Inst Phys European Inst Neuromorph Comp Heidelberg Germany Univ Med Ctr Gottingen Dept Neuroand Sensory Physiol Gottingen Germany

The BrainScaleS-2 (BSS-2) system implements physical models of neurons as well as synapses and aims for an energy-efficient and fast emulation of biological neurons. When replicating neuroscientific experiments on BSS-2, a major challenge is finding suitable model parameters. This study investigates the suitability of the sequential neural posterior estimation (SNPE) algorithm for parameterizing a multi-compartmental neuron model emulated on the BSS-2 analog neuromorphic system. The SNPE algorithm belongs to the class of simulation-based inference methods and estimates the posterior distribution of the model parameters;access to the posterior allows quantifying the confidence in parameter estimations and unveiling correlation between model parameters. For our multi-compartmental model, we show that the approximated posterior agrees with experimental observations and that the identified correlation between parameters fits theoretical expectations. Furthermore, as already shown for software simulations, the algorithm can deal with high-dimensional observations and parameter spaces when the data is generated by emulations on BSS-2. These results suggest that the SNPE algorithm is a promising approach for automating the parameterization and the analyzation of complex models, especially when dealing with characteristic properties of analog neuromorphic substrates, such as trial-to-trial variations or limited parameter ranges.

关键词： analog neuromorphic simulation-based inference multi-compartment

来源：评论

学校读者我要写书评

暂无评论

Hardware-accelerated simulation-based inference of Stochastic Epidemiology Models for COVID-19

引用

ACM JOURNAL ON EMERGING TECHNOLOGIES IN COMPUTING SYSTEMS 2022年第2期18卷 30-30页

作者： Kulkarni, Sourabh Krell, Mario Michael Nabarro, Seth Moritz, Csaba Andras Univ Massachusetts 151 Holdsworth Way Amherst MA 01003 USA Graphcore 167 Hamilton Ave Palo Alto CA 94301 USA Graphcore Res Prudential Bldg Wine St Bristol BS1 2PH Avon England

Epidemiology models are central to understanding and controlling large-scale pandemics. Several epidemiology models require simulation-based inference such as Approximate Bayesian Computation (ABC) to fit their parameters to observations. ABC inference is highly amenable to efficient hardware acceleration. In this work, we develop parallel ABC inference of a stochastic epidemiology model for COVID-19. The statistical inference framework is implemented and compared on Intel's Xeon CPU, NVIDIA's Tesla V100 GPU, Google's V2 Tensor Processing Unit (TAU), and the Graphcore's Mk1 Intelligence Processing Unit (IPU), and the results are discussed in the context of their computational architectures. Results show that TPUs are 3x, GPUs are 4x, and IPUs are 30x faster than Xeon CPUs. Extensive performance analysis indicates that the difference between IPU and GPU can be attributed to higher communication bandwidth, closeness of memory to compute, and higher compute power in the IPU. The proposed framework scales across 16 IPUs, with scaling overhead not exceeding 8% for the experiments performed. We present an example of our framework in practice, performing inference on the epidemiology model across three countries and giving a brief overview of the results.

关键词： simulation-based inference likelihood-free inference COVID-19 epidemiology hardware acceleration performance analysis

来源：评论

学校读者我要写书评

暂无评论

A Physics-Informed, Machine Learning Emulator of a 2D Surface Water Model: What Temporal Networks and simulation-based inference Can Help Us Learn about Hydrologic Processes

引用

WATER 2021年第24期13卷 3633页

作者： Maxwell, Reed M. Condon, Laura E. Melchior, Peter Princeton Univ High Meadows Environm Inst Dept Civil & Environm Engn Princeton NJ 08544 USA Princeton Univ Integrated GroundWater Modeling Ctr Princeton NJ 08544 USA Univ Arizona Dept Hydrol & Atmospher Sci Tucson AZ 85721 USA Princeton Univ Dept Astrophys Sci Princeton NJ 08544 USA Princeton Univ Ctr Stat & Machine Learning Princeton NJ 08544 USA

While machine learning approaches are rapidly being applied to hydrologic problems, physics-informed approaches are still relatively rare. Many successful deep-learning applications have focused on point estimates of streamflow trained on stream gauge observations over time. While these approaches show promise for some applications, there is a need for distributed approaches that can produce accurate two-dimensional results of model states, such as ponded water depth. Here, we demonstrate a 2D emulator of the Tilted V catchment benchmark problem with solutions provided by the integrated hydrology model ParFlow. This emulator model can use 2D Convolution Neural Network (CNN), 3D CNN, and U-Net machine learning architectures and produces time-dependent spatial maps of ponded water depth from which hydrographs and other hydrologic quantities of interest may be derived. A comparison of different deep learning architectures and hyperparameters is presented with particular focus on approaches such as 3D CNN (that have a time-dependent learning component) and 2D CNN and U-Net approaches (that use only the current model state to predict the next state in time). In addition to testing model performance, we also use a simplified simulation based inference approach to evaluate the ability to calibrate the emulator to randomly selected simulations and the match between ML calibrated input parameters and underlying physics-based simulation.

关键词： hydrologic modeling machine learning model emulation hydrologic runoff processes simulation-based inference

来源：评论

学校读者我要写书评

暂无评论

Amortized simulation-based frequentist inference for tractable and intractable likelihoods

引用

MACHINE LEARNING-SCIENCE AND TECHNOLOGY 2024年第1期5卷 015020页

作者： Al Kadhim, Ali Prosper, Harrison B. Prosper, Olivia F. Florida State Univ Dept Phys Tallahassee FL 32306 USA Univ Tennessee Dept Math Knoxville TN 37996 USA

High-fidelity simulators that connect theoretical models with observations are indispensable tools in many sciences. If the likelihood is known, inference can proceed using standard techniques. However, when the likelihood is intractable or unknown, a simulator makes it possible to infer the parameters of a theoretical model directly from real and simulated observations when coupled with machine learning. We introduce an extension of the recently proposed likelihood-free frequentist inference (LF2I) approach that makes it possible to construct confidence sets with the p-value function and to use the same function to check the coverage explicitly at any given parameter point. Like LF2I, this extension yields provably valid confidence sets in parameter inference problems for which a high-fidelity simulator is available. The utility of our algorithm is illustrated by applying it to three pedagogically interesting examples: the first is from cosmology, the second from high-energy physics and astronomy, both with tractable likelihoods, while the third, with an intractable likelihood, is from epidemiology 3 3Code to reproduce all of our results is available on https://***/AliAlkadhim/ALFFI..

关键词： confidence sets likelihood-free inference simulation-based inference frequentist inference likelihood ratio test armotized SBI

来源：评论

学校读者我要写书评

暂无评论

Likelihood and non-parametric Bayesian MCMC inference for spatial point processes based on perfect simulation and path sampling

引用

SCANDINAVIAN JOURNAL OF STATISTICS 2003年第3期30卷 549-564页

作者： Berthelsen, KK Moller, J Univ Aalborg Dept Math Sci DK-9220 Aalborg Denmark

We consider the combination of path sampling and perfect simulation in the context of both likelihood inference and non-parametric Bayesian inference for pairwise interaction point processes. Several empirical results based on simulations and analysis of a data set are presented, and the merits of using perfect simulation are discussed.

关键词： coupling from the past (CFTP) exact simulation likelihood inference Markov chain Monte Carlo multiscale process non-parametric Bayesian smoothing pairwise interaction point process path sampling simulation-based inference Strauss process

来源：评论

学校读者我要写书评

暂无评论

ASPIRE: iterative amortized posterior inference for Bayesian inverse problems

引用

INVERSE PROBLEMS 2025年第4期41卷 045001-045001页

作者： Orozco, Rafael Siahkoohi, Ali Louboutin, Mathias Herrmann, Felix J. Georgia Inst Technol Computat Sci & Engn Atlanta GA 30332 USA Rice Univ Dept Computat Appl Math & Operat Res Houston TX USA Devito Codes Ltd Sr Solut Architect London England

Due to their uncertainty quantification, Bayesian solutions to inverse problems are the framework of choice in applications that are risk averse. These benefits come at the cost of computations that are in general, intractable. New advances in machine learning and variational inference (VI) have lowered this computational barrier by leveraging data-driven learning. Two VI paradigms have emerged that represent different tradeoffs: amortized and non-amortized. Amortized VI can produce fast results but due to generalizing to many observed datasets it produces suboptimal inference results. Non-amortized VI is slower at inference but finds better posterior approximations since it is specialized towards a single observed dataset. Current amortized VI techniques run into a sub-optimality wall that cannot be improved without more expressive neural networks or extra training data. We present a solution that enables iterative improvement of amortized posteriors that uses the same networks architectures and training data. The benefits of our method requires extra computations but these remain frugal since they are based on physics-hybrid methods and summary statistics. Importantly, these computations remain mostly offline thus our method maintains cheap and reusable online evaluation while bridging the optimality gap between these two paradigms. We denote our proposed method ASPIRE - Amortized posteriors with Summaries that are Physics-based and Iteratively REfined. We first validate our method on a stylized problem with a known posterior then demonstrate its practical use on a high-dimensional and nonlinear transcranial medical imaging problem with ultrasound. Compared with the baseline and previous methods in the literature, ASPIRE stands out as an computationally efficient and high-fidelity method for posterior inference.

关键词： Bayesian inference normalizing flows amortized posterior inference simulation-based inference uncertainty quantification

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：