Flow-based models are widely used in generative tasks, including normalizing flow, where a neural network transports from a data distribution $P$ to a normal distribution. This work develops a flow-based model that transports from $P$ to an arbitrary $Q$ where both distributions are only accessible via finite samples. We propose to learn the dynamic optimal transport between $P$ and $Q$ by training a flow neural network. The model is trained to find an invertible transport map between $P$ and $Q$ optimally by minimizing the transport cost. The trained optimal transport flow allows for performing many downstream tasks, including infinitesimal density ratio estimation and distribution interpolation in the latent space for generative models. The effectiveness of the proposed model on high-dimensional data is empirically demonstrated in mutual information estimation, energy-based generative models, and image-to-image translation.
相關內容
This paper addresses the problem of estimating entropy-regularized optimal transport (EOT) maps with squared-Euclidean cost between source and target measures that are subGaussian. In the case that the target measure is compactly supported or strongly log-concave, we show that for a recently proposed in-sample estimator, the expected squared $L^2$-error decays at least as fast as $O(n^{-1/3})$ where $n$ is the sample size. For the general subGaussian case we show that the expected $L^1$-error decays at least as fast as $O(n^{-1/6})$, and in both cases we have polynomial dependence on the regularization parameter. While these results are suboptimal compared to known results in the case of compactness of both the source and target measures (squared $L^2$-error converging at a rate $O(n^{-1})$) and for when the source is subGaussian while the target is compactly supported (squared $L^2$-error converging at a rate $O(n^{-1/2})$), their importance lie in eliminating the compact support requirements. The proof technique makes use of a bias-variance decomposition where the variance is controlled using standard concentration of measure results and the bias is handled by T1-transport inequalities along with sample complexity results in estimation of EOT cost under subGaussian assumptions. Our experimental results point to a looseness in controlling the variance terms and we conclude by posing several open problems.
Deep neural networks are increasingly utilized in mobility prediction tasks, yet their intricate internal workings pose challenges for interpretability, especially in comprehending how various aspects of mobility behavior affect predictions. In this study, we introduce a causal intervention framework to assess the impact of mobility-related factors on neural networks designed for next location prediction -- a task focusing on predicting the immediate next location of an individual. To achieve this, we employ individual mobility models to generate synthetic location visit sequences and control behavior dynamics by intervening in their data generation process. We evaluate the interventional location sequences using mobility metrics and input them into well-trained networks to analyze performance variations. The results demonstrate the effectiveness in producing location sequences with distinct mobility behaviors, thus facilitating the simulation of diverse spatial and temporal changes. These changes result in performance fluctuations in next location prediction networks, revealing impacts of critical mobility behavior factors, including sequential patterns in location transitions, proclivity for exploring new locations, and preferences in location choices at population and individual levels. The gained insights hold significant value for the real-world application of mobility prediction networks, and the framework is expected to promote the use of causal inference for enhancing the interpretability and robustness of neural networks in mobility applications.
We address the problem of configuring a power distribution network with reliability and resilience objectives by satisfying the demands of the consumers and saturating each production source as little as possible. We consider power distribution networks containing source nodes producing electricity, nodes representing electricity consumers and switches between them. Configuring this network consists in deciding the orientation of the links between the nodes of the network. The electric flow is a direct consequence of the chosen configuration and can be computed in polynomial time. It is valid if it satisfies the demand of each consumer and capacity constraints on the network. In such a case, we study the problem of determining a feasible solution that balances the loads of the sources, that is their production rates. We use three metrics to measure the quality of a solution: minimizing the maximum load, maximizing the minimum load and minimizing the difference of the maximum and the minimum loads. This defines optimization problems called respectively min-M, max-m and min-R. In the case where the graph of the network is a tree, it is known that the problem of building a valid configuration is polynomial. We show the three optimization variants have distinct properties regarding the theoretical complexity and the approximability. Particularly, we show that min-M is polynomial, that max-m is NP-Hard but belongs to the class FPTAS and that min-R is NP-Hard, cannot 1 be approximated to within any exponential relative ratio but, for any $\epsilon$ > 0, there exists an algorithm for which the value of the returned solution equals the value of an optimal solution shifted by at most $\epsilon$.
Accurate simulation of deformable linear object (DLO) dynamics is challenging if the task at hand requires a human-interpretable model that also yields fast predictions. To arrive at such a model, we draw inspiration from the rigid finite element method (R-FEM) and model a DLO as a serial chain of rigid bodies whose internal state is unrolled through time by a dynamics network. As this state is not observed directly, the dynamics network is trained jointly with a physics-informed encoder which maps observed motion variables to the DLO's hidden state. To encourage that the state acquires a physically meaningful representation, we leverage the forward kinematics of the underlying R-FEM model as a decoder. Through robot experiments we demonstrate that the proposed architecture provides an easy-to-handle, yet capable DLO dynamics model yielding physically interpretable predictions from partial observations. The project code is available at: \url{//tinyurl.com/fei-networks}
The emergence of new applications brings multi-class traffic with diverse quality of service (QoS) requirements to wide area networks (WANs), motivating research in traffic engineering (TE). In recent years, novel centralized and hierarchical TE schemes have used heuristic or machine learning techniques to orchestrate resources in closed systems such as datacenter networks. However, these schemes suffer from long delivery delays and high control overhead when applied to general WANs. To provide low-delay services, this paper proposes an asynchronous multi-class traffic management (AMTM) scheme. We first establish an asynchronous TE paradigm in which distributed nodes locally perform low-complexity and low-delay traffic control based on link prices, and the TE server updates link prices to eliminate decision conflicts between edge nodes. By modeling the asynchronous TE paradigm as a control system with non-negligible control loop delay, we find that the traditional pricing strategy cannot simultaneously achieve a low packet loss rate and a low flow delivery delay. To address this issue, we propose a new pricing strategy based on the observations of virtual queues in intermediate nodes. We also present a system design and related algorithms that utilize a dynamic step size mechanism of link price update. Simulation results show that AMTM can effectively reduce the end-to-end flow delivery delay.
We observe a large variety of robots in terms of their bodies, sensors, and actuators. Given the commonalities in the skill sets, teaching each skill to each different robot independently is inefficient and not scalable when the large variety in the robotic landscape is considered. If we can learn the correspondences between the sensorimotor spaces of different robots, we can expect a skill that is learned in one robot can be more directly and easily transferred to other robots. In this paper, we propose a method to learn correspondences among two or more robots that may have different morphologies. To be specific, besides robots with similar morphologies with different degrees of freedom, we show that a fixed-based manipulator robot with joint control and a differential drive mobile robot can be addressed within the proposed framework. To set up the correspondence among the robots considered, an initial base task is demonstrated to the robots to achieve the same goal. Then, a common latent representation is learned along with the individual robot policies for achieving the goal. After the initial learning stage, the observation of a new task execution by one robot becomes sufficient to generate a latent space representation pertaining to the other robots to achieve the same task. We verified our system in a set of experiments where the correspondence between robots is learned (1) when the robots need to follow the same paths to achieve the same task, (2) when the robots need to follow different trajectories to achieve the same task, and (3) when complexities of the required sensorimotor trajectories are different for the robots. We also provide a proof-of-the-concept realization of correspondence learning between a real manipulator robot and a simulated mobile robot.
We propose FNETS, a methodology for network estimation and forecasting of high-dimensional time series exhibiting strong serial- and cross-sectional correlations. We operate under a factor-adjusted vector autoregressive (VAR) model which, after accounting for pervasive co-movements of the variables by {\it common} factors, models the remaining {\it idiosyncratic} dynamic dependence between the variables as a sparse VAR process. Network estimation of FNETS consists of three steps: (i) factor-adjustment via dynamic principal component analysis, (ii) estimation of the latent VAR process via $\ell_1$-regularised Yule-Walker estimator, and (iii) estimation of partial correlation and long-run partial correlation matrices. In doing so, we learn three networks underpinning the VAR process, namely a directed network representing the Granger causal linkages between the variables, an undirected one embedding their contemporaneous relationships and finally, an undirected network that summarises both lead-lag and contemporaneous linkages. In addition, FNETS provides a suite of methods for forecasting the factor-driven and the idiosyncratic VAR processes. Under general conditions permitting tails heavier than the Gaussian one, we derive uniform consistency rates for the estimators in both network estimation and forecasting, which hold as the dimension of the panel and the sample size diverge. Simulation studies and real data application confirm the good performance of FNETS.
The term "Normalizing Flows" is related to the task of constructing invertible transport maps between probability measures by means of deep neural networks. In this paper, we consider the problem of recovering the $W_2$-optimal transport map $T$ between absolutely continuous measures $\mu,\nu\in\mathcal{P}(\mathbb{R}^n)$ as the flow of a linear-control neural ODE. We first show that, under suitable assumptions on $\mu,\nu$ and on the controlled vector fields, the optimal transport map is contained in the $C^0_c$-closure of the flows generated by the system. Assuming that discrete approximations $\mu_N,\nu_N$ of the original measures $\mu,\nu$ are available, we use a discrete optimal coupling $\gamma_N$ to define an optimal control problem. With a $\Gamma$-convergence argument, we prove that its solutions correspond to flows that approximate the optimal transport map $T$. Finally, taking advantage of the Pontryagin Maximum Principle, we propose an iterative numerical scheme for the resolution of the optimal control problem, resulting in an algorithm for the practical computation of the approximated optimal transport map.
Advancements in materials play a crucial role in technological progress. However, the process of discovering and developing materials with desired properties is often impeded by substantial experimental costs, extensive resource utilization, and lengthy development periods. To address these challenges, modern approaches often employ machine learning (ML) techniques such as Bayesian Optimization (BO), which streamline the search for optimal materials by iteratively selecting experiments that are most likely to yield beneficial results. However, traditional BO methods, while beneficial, often struggle with balancing the trade-off between exploration and exploitation, leading to sub-optimal performance in material discovery processes. This paper introduces a novel Threshold-Driven UCB-EI Bayesian Optimization (TDUE-BO) method, which dynamically integrates the strengths of Upper Confidence Bound (UCB) and Expected Improvement (EI) acquisition functions to optimize the material discovery process. Unlike the classical BO, our method focuses on efficiently navigating the high-dimensional material design space (MDS). TDUE-BO begins with an exploration-focused UCB approach, ensuring a comprehensive initial sweep of the MDS. As the model gains confidence, indicated by reduced uncertainty, it transitions to the more exploitative EI method, focusing on promising areas identified earlier. The UCB-to-EI switching policy dictated guided through continuous monitoring of the model uncertainty during each step of sequential sampling results in navigating through the MDS more efficiently while ensuring rapid convergence. The effectiveness of TDUE-BO is demonstrated through its application on three different material datasets, showing significantly better approximation and optimization performance over the EI and UCB-based BO methods in terms of the RMSE scores and convergence efficiency, respectively.
Recent advances in 3D fully convolutional networks (FCN) have made it feasible to produce dense voxel-wise predictions of volumetric images. In this work, we show that a multi-class 3D FCN trained on manually labeled CT scans of several anatomical structures (ranging from the large organs to thin vessels) can achieve competitive segmentation results, while avoiding the need for handcrafting features or training class-specific models. To this end, we propose a two-stage, coarse-to-fine approach that will first use a 3D FCN to roughly define a candidate region, which will then be used as input to a second 3D FCN. This reduces the number of voxels the second FCN has to classify to ~10% and allows it to focus on more detailed segmentation of the organs and vessels. We utilize training and validation sets consisting of 331 clinical CT images and test our models on a completely unseen data collection acquired at a different hospital that includes 150 CT scans, targeting three anatomical organs (liver, spleen, and pancreas). In challenging organs such as the pancreas, our cascaded approach improves the mean Dice score from 68.5 to 82.2%, achieving the highest reported average score on this dataset. We compare with a 2D FCN method on a separate dataset of 240 CT scans with 18 classes and achieve a significantly higher performance in small organs and vessels. Furthermore, we explore fine-tuning our models to different datasets. Our experiments illustrate the promise and robustness of current 3D FCN based semantic segmentation of medical images, achieving state-of-the-art results. Our code and trained models are available for download: //github.com/holgerroth/3Dunet_abdomen_cascade.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191