PyTorchKR Papers

최신 논문

총 307편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2107.11770공식 코드 · Papers with Code

Data-based stochastic modeling reveals sources of activity bursts in single-cell TGF-$β$ signaling

Cells sense their surrounding by employing intracellular signaling pathways that transmit hormonal signals from the cell membrane to the nucleus. TGF-$\beta$/SMAD signaling encodes various cell fates, controls tissue homeostasis and is deregulated in diseases such as cancer. The pathway shows strong heterogeneity at the single-cell level, but quantitative insights into mechanisms underlying fluctuations at various time scales are still missing, partly due to inefficiency in the calibration of stochastic models that mechanistically describe signaling processes. In this work we analyze single-cell TGF-$\beta$/SMAD signaling and show that it exhibits temporal stochastic bursts which are dose-dependent and whose number and magnitude correlate with cell migration. We propose a stochastic modeling approach to mechanistically describe these pathway fluctuations with high computational efficiency. Employing high-order numerical integration and fitting to burst statistics we enable efficient quantitative parameter estimation and discriminate models that assume noise in different reactions at the receptor level. This modeling approach suggests that stochasticity in the internalization of TGF-$\beta$ receptors into endosomes plays a key role in the observed temporal bursting. Further, the model predicts the single-cell dynamics of TGF-$\beta$/SMAD signaling in untested conditions, e.g., successfully reflects memory effects of signaling noise and cellular sensitivity towards repeated stimulation. Taken together, our computational framework based on burst analysis, noise modeling and path computation scheme is a suitable tool for the data-based modeling of complex signaling pathways, capable of identifying the source of temporal noise.

arXiv:2106.12594공식 코드 · Papers with Code

Real-time gravitational-wave science with neural posterior estimation

We demonstrate unprecedented accuracy for rapid gravitational-wave parameter estimation with deep learning. Using neural networks as surrogates for Bayesian posterior distributions, we analyze eight gravitational-wave events from the first LIGO-Virgo Gravitational-Wave Transient Catalog and find very close quantitative agreement with standard inference codes, but with inference times reduced from O(day) to a minute per event. Our networks are trained using simulated data, including an estimate of the detector-noise characteristics near the event. This encodes the signal and noise models within millions of neural-network parameters, and enables inference for any observed data consistent with the training distribution, accounting for noise nonstationarity from event to event. Our algorithm -- called "DINGO" -- sets a new standard in fast-and-accurate inference of physical parameters of detected gravitational-wave events, which should enable real-time data analysis without sacrificing accuracy.

arXiv:2106.05190공식 코드 · Papers with Code

DPER: Efficient Parameter Estimation for Randomly Missing Data

The missing data problem has been broadly studied in the last few decades and has various applications in different areas such as statistics or bioinformatics. Even though many methods have been developed to tackle this challenge, most of those are imputation techniques that require multiple iterations through the data before yielding convergence. In addition, such approaches may introduce extra biases and noises to the estimated parameters. In this work, we propose novel algorithms to find the maximum likelihood estimates (MLEs) for a one-class/multiple-class randomly missing data set under some mild assumptions. As the computation is direct without any imputation, our algorithms do not require multiple iterations through the data, thus promising to be less time-consuming than other methods while maintaining superior estimation performance. We validate these claims by empirical results on various data sets of different sizes and release all codes in a GitHub repository to contribute to the research community related to this problem.

arXiv:2106.04802공식 코드 · Papers with Code

Probabilistic task modelling for meta-learning

We propose probabilistic task modelling -- a generative probabilistic model for collections of tasks used in meta-learning. The proposed model combines variational auto-encoding and latent Dirichlet allocation to model each task as a mixture of Gaussian distribution in an embedding space. Such modelling provides an explicit representation of a task through its task-theme mixture. We present an efficient approximation inference technique based on variational inference method for empirical Bayes parameter estimation. We perform empirical evaluations to validate the task uncertainty and task distance produced by the proposed method through correlation diagrams of the prediction accuracy on testing tasks. We also carry out experiments of task selection in meta-learning to demonstrate how the task relatedness inferred from the proposed model help to facilitate meta-learning algorithms.

arXiv:2106.03340공식 코드 · Papers with Code

Instrument Space Selection for Kernel Maximum Moment Restriction

Kernel maximum moment restriction (KMMR) recently emerges as a popular framework for instrumental variable (IV) based conditional moment restriction (CMR) models with important applications in conditional moment (CM) testing and parameter estimation for IV regression and proximal causal learning. The effectiveness of this framework, however, depends critically on the choice of a reproducing kernel Hilbert space (RKHS) chosen as a space of instruments. In this work, we presents a systematic way to select the instrument space for parameter estimation based on a principle of the least identifiable instrument space (LIIS) that identifies model parameters with the least space complexity. Our selection criterion combines two distinct objectives to determine such an optimal space: (i) a test criterion to check identifiability; (ii) an information criterion based on the effective dimension of RKHSs as a complexity measure. We analyze the consistency of our method in determining the LIIS, and demonstrate its effectiveness for parameter estimation via simulations.

arXiv:2106.02078공식 코드 · Papers with Code

Improving Neural Network Robustness via Persistency of Excitation

Improving adversarial robustness of neural networks remains a major challenge. Fundamentally, training a neural network via gradient descent is a parameter estimation problem. In adaptive control, maintaining persistency of excitation (PoE) is integral to ensuring convergence of parameter estimates in dynamical systems to their true values. We show that parameter estimation with gradient descent can be modeled as a sampling of an adaptive linear time-varying continuous system. Leveraging this model, and with inspiration from Model-Reference Adaptive Control (MRAC), we prove a sufficient condition to constrain gradient descent updates to reference persistently excited trajectories converging to the true parameters. The sufficient condition is achieved when the learning rate is less than the inverse of the Lipschitz constant of the gradient of loss function. We provide an efficient technique for estimating the corresponding Lipschitz constant in practice using extreme value theory. Our experimental results in both standard and adversarial training illustrate that networks trained with the PoE-motivated learning rate schedule have similar clean accuracy but are significantly more robust to adversarial attacks than models trained using current state-of-the-art heuristics.

arXiv:2105.13440공식 코드 · Papers with Code

Non-negative matrix factorization algorithms greatly improve topic model fits

We report on the potential for using algorithms for non-negative matrix factorization (NMF) to improve parameter estimation in topic models. While several papers have studied connections between NMF and topic models, none have suggested leveraging these connections to develop new algorithms for fitting topic models. NMF avoids the "sum-to-one" constraints on the topic model parameters, resulting in an optimization problem with simpler structure and more efficient computations. Building on recent advances in optimization algorithms for NMF, we show that first solving the NMF problem then recovering the topic model fit can produce remarkably better fits, and in less time, than standard algorithms for topic models. While we focus primarily on maximum likelihood estimation, we show that this approach also has the potential to improve variational inference for topic models. Our methods are implemented in the R package fastTopics.

arXiv:2105.13136공식 코드 · Papers with Code

A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networks

This work is the first to employ and adapt the image-to-image translation concept based on conditional generative adversarial networks (cGAN) towards learning a forward and an inverse solution operator of partial differential equations (PDEs). Even though the proposed framework could be applied as a surrogate model for the solution of any PDEs, here we focus on steady-state solutions of coupled hydro-mechanical processes in heterogeneous porous media. Strongly heterogeneous material properties, which translate to the heterogeneity of coefficients of the PDEs and discontinuous features in the solutions, require specialized techniques for the forward and inverse solution of these problems. Additionally, parametrization of the spatially heterogeneous coefficients is excessively difficult by using standard reduced order modeling techniques. In this work, we overcome these challenges by employing the image-to-image translation concept to learn the forward and inverse solution operators and utilize a U-Net generator and a patch-based discriminator. Our results show that the proposed data-driven reduced order model has competitive predictive performance capabilities in accuracy and computational efficiency as well as training time requirements compared to state-of-the-art data-driven methods for both forward and inverse problems.

arXiv:2105.12008공식 코드 · Papers with Code

A protocol for dynamic model calibration

Ordinary differential equation models are nowadays widely used for the mechanistic description of biological processes and their temporal evolution. These models typically have many unknown and non-measurable parameters, which have to be determined by fitting the model to experimental data. In order to perform this task, known as parameter estimation or model calibration, the modeller faces challenges such as poor parameter identifiability, lack of sufficiently informative experimental data, and the existence of local minima in the objective function landscape. These issues tend to worsen with larger model sizes, increasing the computational complexity and the number of unknown parameters. An incorrectly calibrated model is problematic because it may result in inaccurate predictions and misleading conclusions. For non-expert users, there are a large number of potential pitfalls. Here, we provide a protocol that guides the user through all the steps involved in the calibration of dynamic models. We illustrate the methodology with two models, and provide all the code required to reproduce the results and perform the same analysis on new models. Our protocol provides practitioners and researchers in biological modelling with a one-stop guide that is at the same time compact and sufficiently comprehensive to cover all aspects of the problem.

arXiv:2105.04379공식 코드 · Papers with Code

Gradient-based Bayesian Experimental Design for Implicit Models using Mutual Information Lower Bounds

We introduce a framework for Bayesian experimental design (BED) with implicit models, where the data-generating distribution is intractable but sampling from it is still possible. In order to find optimal experimental designs for such models, our approach maximises mutual information lower bounds that are parametrised by neural networks. By training a neural network on sampled data, we simultaneously update network parameters and designs using stochastic gradient-ascent. The framework enables experimental design with a variety of prominent lower bounds and can be applied to a wide range of scientific tasks, such as parameter estimation, model discrimination and improving future predictions. Using a set of intractable toy models, we provide a comprehensive empirical comparison of prominent lower bounds applied to the aforementioned tasks. We further validate our framework on a challenging system of stochastic differential equations from epidemiology.

arXiv:2103.13416공식 코드 · Papers with Code

Mixture Density Network Estimation of Continuous Variable Maximum Likelihood Using Discrete Training Samples

Mixture Density Networks (MDNs) can be used to generate probability density functions of model parameters $\boldsymbol{\theta}$ given a set of observables $\mathbf{x}$. In some applications, training data are available only for discrete values of a continuous parameter $\boldsymbol{\theta}$. In such situations a number of performance-limiting issues arise which can result in biased estimates. We demonstrate the usage of MDNs for parameter estimation, discuss the origins of the biases, and propose a corrective method for each issue.

arXiv:2009.04237공식 코드 · Papers with Code

Hyperspectral Image Super-Resolution via Deep Prior Regularization with Parameter Estimation

Hyperspectral image (HSI) super-resolution is commonly used to overcome the hardware limitations of existing hyperspectral imaging systems on spatial resolution. It fuses a low-resolution (LR) HSI and a high-resolution (HR) conventional image of the same scene to obtain an HR HSI. In this work, we propose a method that integrates a physical model and deep prior information. Specifically, a novel, yet effective two-stream fusion network is designed to serve as a {regularizer} for the fusion problem. This fusion problem is formulated as an optimization problem whose solution can be obtained by solving a Sylvester equation. Furthermore, the regularization parameter is simultaneously estimated to automatically adjust contribution of the physical model and {the} learned prior to reconstruct the final HR HSI. Experimental results on {both simulated and real data} demonstrate the superiority of the proposed method over other state-of-the-art methods on both quantitative and qualitative comparisons.

arXiv:2102.10773공식 코드 · Papers with Code

Slowly Varying Regression under Sparsity

We present the framework of slowly varying regression under sparsity, allowing sparse regression models to exhibit slow and sparse variations. The problem of parameter estimation is formulated as a mixed-integer optimization problem. We demonstrate that it can be precisely reformulated as a binary convex optimization problem through a novel relaxation technique. This relaxation involves a new equality on Moore-Penrose inverses, convexifying the non-convex objective function while matching the original objective on all feasible binary points. This enables us to efficiently solve the problem to provable optimality using a cutting plane-type algorithm. We develop a highly optimized implementation of this algorithm, substantially improving upon the asymptotic computational complexity of a straightforward implementation. Additionally, we propose a fast heuristic method that guarantees a feasible solution and, as empirically illustrated, produces high-quality warm-start solutions for the binary optimization problem. To tune the framework's hyperparameters, we suggest a practical procedure relying on binary search that, under certain assumptions, is guaranteed to recover the true model parameters. On both synthetic and real-world datasets, we demonstrate that the resulting algorithm outperforms competing formulations in comparable times across various metrics, including estimation accuracy, predictive power, and computational time. The algorithm is highly scalable, allowing us to train models with thousands of parameters. Our implementation is available open-source at https://github.com/vvdigalakis/SSVRegression.git.

arXiv:2102.08232공식 코드 · Papers with Code

The MELODIC family for simultaneous binary logistic regression in a reduced space

Logistic regression is a commonly used method for binary classification. Researchers often have more than a single binary response variable and simultaneous analysis is beneficial because it provides insight into the dependencies among response variables as well as between the predictor variables and the responses. Moreover, in such a simultaneous analysis the equations can lend each other strength, which might increase predictive accuracy. In this paper, we propose the MELODIC family for simultaneous binary logistic regression modeling. In this family, the regression models are defined in a Euclidean space of reduced dimension, based on a distance rule. The model may be interpreted in terms of logistic regression coefficients or in terms of a biplot. We discuss a fast iterative majorization (or MM) algorithm for parameter estimation. Two applications are shown in detail: one relating personality characteristics to drug consumption profiles and one relating personality characteristics to depressive and anxiety disorders. We present a thorough comparison of our MELODIC family with alternative approaches for multivariate binary data.

arXiv:2102.07064공식 코드 · Papers with Code

NeRF--: Neural Radiance Fields Without Known Camera Parameters

Considering the problem of novel view synthesis (NVS) from only a set of 2D images, we simplify the training process of Neural Radiance Field (NeRF) on forward-facing scenes by removing the requirement of known or pre-computed camera parameters, including both intrinsics and 6DoF poses. To this end, we propose NeRF$--$, with three contributions: First, we show that the camera parameters can be jointly optimised as learnable parameters with NeRF training, through a photometric reconstruction; Second, to benchmark the camera parameter estimation and the quality of novel view renderings, we introduce a new dataset of path-traced synthetic scenes, termed as Blender Forward-Facing Dataset (BLEFF); Third, we conduct extensive analyses to understand the training behaviours under various camera motions, and show that in most scenarios, the joint optimisation pipeline can recover accurate camera parameters and achieve comparable novel view synthesis quality as those trained with COLMAP pre-computed camera parameters. Our code and data are available at https://nerfmm.active.vision.

arXiv:2011.08152공식 코드 · Papers with Code

LUCIDGames: onLine UnsCented Inverse Dynamic Games forAdaptive Trajectory Prediction and Planning

Existing game-theoretic planning methods assumethat the robot knows the objective functions of the other agentsa prioriwhile, in practical scenarios, this is rarely the case.This paper introduces LUCIDGames, an inverse optimal controlalgorithm that is able to estimate the other agents’ objectivefunctions in real time, and incorporate those estimates onlineinto a receding-horizon game-theoretic planner. LUCIDGamessolves the inverse optimal control problem by recasting itin a recursive parameter-estimation framework. LUCIDGamesuses an unscented Kalman filter (UKF) to iteratively update aBayesian estimate of the other agents’ cost function parameters,improving that estimate online as more data is gathered fromthe other agents’ observed trajectories. The planner then takesaccount of the uncertainty in the Bayesian parameter estimatesof other agents by planning a trajectory for the robot subjectto uncertainty ellipse constraints. The algorithm assumes noexplicit communication or coordination between the robot andthe other agents in the environment. An MPC implementationof LUCIDGames demonstrates real-time performance on com-plex autonomous driving scenarios with an update frequencyof 40 Hz. Empirical results demonstrate that LUCIDGamesimproves the robot’s performance over existing game-theoreticand traditional MPC planning approaches. Our implementa-tion of LUCIDGames is available athttps://github.com/RoboticExplorationLab/LUCIDGames.jl

arXiv:2012.15339공식 코드 · Papers with Code

Fast covariance parameter estimation of spatial Gaussian process models using neural networks

Gaussian processes (GPs) are a popular model for spatially referenced data and allow descriptive statements, predictions at new locations, and simulation of new fields. Often a few parameters are sufficient to parameterize the covariance function, and maximum likelihood (ML) methods can be used to estimate these parameters from data. ML methods, however, are computationally demanding. For example, in the case of local likelihood estimation, even fitting covariance models on modest size windows can overwhelm typical computational resources for data analysis. This limitation motivates the idea of using neural network (NN) methods to approximate ML estimates. We train NNs to take moderate size spatial fields or variograms as input and return the range and noise-to-signal covariance parameters. Once trained, the NNs provide estimates with a similar accuracy compared to ML estimation and at a speedup by a factor of 100 or more. Although we focus on a specific covariance estimation problem motivated by a climate science application, this work can be easily extended to other, more complex, spatial problems and provides a proof-of-concept for this use of machine learning in computational statistics.

arXiv:2012.10861공식 코드 · Papers with Code

Memory AMP

Approximate message passing (AMP) is a low-cost iterative parameter-estimation technique for certain high-dimensional linear systems with non-Gaussian distributions. AMP only applies to independent identically distributed (IID) transform matrices, but may become unreliable (e.g., perform poorly or even diverge) for other matrix ensembles, especially for ill-conditioned ones. To solve this issue, orthogonal/vector AMP (OAMP/VAMP) was proposed for general right-unitarily-invariant matrices. However, the Bayes-optimal OAMP/VAMP (BO-OAMP/VAMP) requires a high-complexity linear minimum mean square error (MMSE) estimator. This prevents OAMP/VAMP from being used in large-scale systems. To address the drawbacks of AMP and BO-OAMP/VAMP, this paper offers a memory AMP (MAMP) framework based on the orthogonality principle, which ensures that estimation errors in MAMP are asymptotically IID Gaussian. To realize the required orthogonality for MAMP, we provide an orthogonalization procedure for the local memory estimators. In addition, we propose a Bayes-optimal MAMP (BO-MAMP), in which a long-memory matched filter is used for interference suppression. The complexity of BO-MAMP is comparable to AMP. To asymptotically characterize the performance of BO-MAMP, a state evolution is derived. The relaxation parameters and damping vector in BO-MAMP are optimized based on state evolution. Most crucially, the state evolution of the optimized BO-MAMP converges to the same fixed point as that of the high-complexity BO-OAMP/VAMP for all right-unitarily-invariant matrices, and achieves the Bayes optimal MSE predicted by the replica method if its state evolution has a unique fixed point. Finally, simulations are provided to verify the theoretical results' validity and accuracy.

arXiv:2012.09122공식 코드 · Papers with Code

AMICI: High-Performance Sensitivity Analysis for Large Ordinary Differential Equation Models

Ordinary differential equation models facilitate the understanding of cellular signal transduction and other biological processes. However, for large and comprehensive models, the computational cost of simulating or calibrating can be limiting. AMICI is a modular toolbox implemented in C++/Python/MATLAB that provides efficient simulation and sensitivity analysis routines tailored for scalable, gradient-based parameter estimation and uncertainty quantification. AMICI is published under the permissive BSD-3-Clause license with source code publicly available on https://github.com/AMICI-dev/AMICI. Citeable releases are archived on Zenodo.

arXiv:2012.06691공식 코드 · Papers with Code

Parameter Estimation with Dense and Convolutional Neural Networks Applied to the FitzHugh-Nagumo ODE

Machine learning algorithms have been successfully used to approximate nonlinear maps under weak assumptions on the structure and properties of the maps. We present deep neural networks using dense and convolutional layers to solve an inverse problem, where we seek to estimate parameters of a FitzHugh-Nagumo model, which consists of a nonlinear system of ordinary differential equations (ODEs). We employ the neural networks to approximate reconstruction maps for model parameter estimation from observational data, where the data comes from the solution of the ODE and takes the form of a time series representing dynamically spiking membrane potential of a biological neuron. We target this dynamical model because of the computational challenges it poses in an inference setting, namely, having a highly nonlinear and nonconvex data misfit term and permitting only weakly informative priors on parameters. These challenges cause traditional optimization to fail and alternative algorithms to exhibit large computational costs. We quantify the prediction errors of model parameters obtained from the neural networks and investigate the effects of network architectures with and without the presence of noise in observational data. We generalize our framework for neural network-based reconstruction maps to simultaneously estimate ODE parameters and parameters of autocorrelated observational noise. Our results demonstrate that deep neural networks have the potential to estimate parameters in dynamical models and stochastic processes, and they are capable of predicting parameters accurately for the FitzHugh-Nagumo model.