Search

Network meta-analysis (NMA) is an extension of pairwise meta-analysis which facilitates the estimation of relative effects for multiple competing treatments. A hierarchy of treatments is a useful output of an NMA. Treatment hierarchies are produced using ranking metrics. Common ranking metrics include the Surface Under the Cumulative RAnking curve (SUCRA) and P-scores, which are the frequentist analogue to SUCRAs. Both metrics consider the size and uncertainty of the estimated treatment effects, with larger values indicating a more preferred treatment. Although SUCRAs and P-scores themselves consider uncertainty, treatment hierarchies produced by these ranking metrics are typically reported without a measure of certainty, which might be misleading to practitioners. We propose a new metric, Precision of Treatment Hierarchy (POTH), which quantifies the certainty in producing a treatment hierarchy from SUCRAs or P-scores. The metric connects three statistical quantities: The variance of the SUCRA values, the variance of the mean rank of each treatment, and the average variance of the distribution of individual ranks for each treatment. POTH provides a single, interpretable value which quantifies the degree of certainty in producing a treatment hierarchy. We show how the metric can be adapted to apply to subsets of treatments in a network, for example, to quantify the certainty in the hierarchy of the top three treatments. We calculate POTH for a database of NMAs to investigate its empirical properties, and we demonstrate its use on three published networks., Comment: 15 pages, 9 figures

Spiking neural networks (SNNs) have captured apparent interest over the recent years, stemming from neuroscience and reaching the field of artificial intelligence. However, due to their nature SNNs remain far behind in achieving the exceptional performance of deep neural networks (DNNs). As a result, many scholars are exploring ways to enhance SNNs by using learning techniques from DNNs. While this approach has been proven to achieve considerable improvements in SNN performance, we propose another perspective: enhancing the biological plausibility of the models to leverage the advantages of SNNs fully. Our approach aims to propose a brain-like combination of audio-visual signal processing for recognition tasks, intended to succeed in more bio-plausible human-robot interaction applications.

We introduce a real-time identification method for discrete-time state-dependent switching systems in both the input--output and state-space domains. In particular, we design a system of adaptive algorithms running in two timescales; a stochastic approximation algorithm implements an online deterministic annealing scheme at a slow timescale and estimates the mode-switching signal, and an recursive identification algorithm runs at a faster timescale and updates the parameters of the local models based on the estimate of the switching signal. We first focus on piece-wise affine systems and discuss identifiability conditions and convergence properties based on the theory of two-timescale stochastic approximation. In contrast to standard identification algorithms for switched systems, the proposed approach gradually estimates the number of modes and is appropriate for real-time system identification using sequential data acquisition. The progressive nature of the algorithm improves computational efficiency and provides real-time control over the performance-complexity trade-off. Finally, we address specific challenges that arise in the application of the proposed methodology in identification of more general switching systems. Simulation results validate the efficacy of the proposed methodology.

What role do non-elected bureaucrats play when elections provide imperfect accountability and create incentives for pandering? We develop a model where politicians and bureaucrats interact to implement policy. Both can either be good, sharing the voters' preferences over policies, or bad, intent on enacting policies that favor special interests. Our analysis identifies the conditions under which good bureaucrats choose to support or oppose political pandering. When bureaucrats wield significant influence over policy decisions, good politicians lose their incentives to pander, a shift that ultimately benefits voters. An intermediate level of bureaucratic influence over policymaking can be voter-optimal: large enough to prevent pandering but small enough to avoid granting excessive influence to potentially bad bureaucrats.

Modern GPU applications, such as machine learning (ML), can only partially utilize GPUs, leading to GPU underutilization in cloud environments. Sharing GPUs across multiple applications from different tenants can improve resource utilization and consequently cost, energy, and power efficiency. However, GPU sharing creates memory safety concerns because kernels must share a single GPU address space. Existing spatial-sharing mechanisms either lack fault isolation for memory accesses or require static partitioning, which leads to limited deployability or low utilization. In this paper, we present Guardian, a PTX-level bounds checking approach that provides memory isolation and supports dynamic GPU spatial-sharing. Guardian relies on three mechanisms: (1) It divides the common GPU address space into separate partitions for different applications. (2) It intercepts and checks all GPU related calls at the lowest level, fencing erroneous operations. (3) It instruments all GPU kernels at the PTX level -- available in closed GPU libraries -- fencing all kernel memory accesses outside application memory bounds. Guardian's approach is transparent to applications and supports real-life frameworks, such as Caffe and PyTorch, that issue billions of GPU kernels. Our evaluation shows that Guardian's overhead compared to native for such frameworks is between 4% - 12% and on average 9%.

Safe overtaking, especially in a bidirectional mixed-traffic setting, remains a key challenge for Connected Autonomous Vehicles (CAVs). The presence of human-driven vehicles (HDVs), behavior unpredictability, and blind spots resulting from sensor occlusion make this a challenging control problem. To overcome these difficulties, we propose a cooperative communication-based approach that utilizes the information shared between CAVs to reduce the effects of sensor occlusion while benefiting from the local velocity prediction based on past tracking data. Our control framework aims to perform overtaking maneuvers with the objective of maximizing velocity while prioritizing safety and passenger comfort. Our method is also capable of reactively adjusting its plan to dynamic changes in the environment. The performance of the proposed approach is verified using realistic traffic simulations., Comment: Published in: 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

In this work, we study the inverse problem of identifying complex flocking dynamics in a domain cluttered with obstacles. We get inspiration from animal flocks moving in complex ways with capabilities far beyond what current robots can do. Owing to the difficulty of observing and recovering the trajectories of the agents, we focus on the dynamics of their probability densities, which are governed by partial differential equations (PDEs), namely compressible Euler equations subject to non-local forces. We formulate the inverse problem of learning interactions as a PDE-constrained optimization problem of minimizing the squared Hellinger distance between the histogram of the flock and the distribution associated to our PDEs. The numerical methods used to efficiently solve the PDE-constrained optimization problem are described. Realistic flocking data are simulated using the Boids model of flocking agents, which differs in nature from the reconstruction models used in our PDEs. Our analysis and simulated experiments show that the behavior of cohesive flocks can be recovered accurately with approximate PDE solutions., Comment: 6 pages, 5 figures, submitted to IEEE CDC 2023

Today, using multiple heterogeneous accelerators efficiently from applications and high-level frameworks, such as TensorFlow and Caffe, poses significant challenges in three respects: (a) sharing accelerators, (b) allocating available resources elastically during application execution, and (c) reducing the required programming effort. In this paper, we present Arax, a runtime system that decouples applications from heterogeneous accelerators within a server. First, Arax maps application tasks dynamically to available resources, managing all required task state, memory allocations, and task dependencies. As a result, Arax can share accelerators across applications in a server and adjust the resources used by each application as load fluctuates over time. dditionally, Arax offers a simple API and includes Autotalk, a stub generator that automatically generates stub libraries for applications already written for specific accelerator types, such as NVIDIA GPUs. Consequently, Arax applications are written once without considering physical details, including the number and type of accelerators. Our results show that applications, such as Caffe, TensorFlow, and Rodinia, can run using Arax with minimum effort and low overhead compared to native execution, about 12% (geometric mean). Arax supports efficient accelerator sharing, by offering up to 20% improved execution times compared to NVIDIA MPS, which supports NVIDIA GPUs only. Arax can transparently provide elasticity, decreasing total application turn-around time by up to 2x compared to native execution without elasticity support.

A geometrical method is used for the analysis of stochastic processes in plasma turbulence. Distances between thermodynamic states can be computed according the thermodynamic length methodology which allows the use of a Riemannian metric on the phase space. A geometric methodology is suitable in order to understand stochastic processes involved in e.g. order-disorder transition, where a sudden increase in distance is expected. Gyrokinetic simulations of Ion-Temperature-Gradient (ITG) mode driven turbulence in the core-region of the stellarator W7-X, with realistic quasi-isodynamic topologies are considered. In gyrokinetic plasma turbulence simulations avalanches, e.g. of heat and particles, are often found and in this work a novel method for detection is investigated. This new method combines the Singular Spectrum Analysis algorithm and Hierarchical Clustering such that the gyrokinetic simulation time series is decomposed into a part of useful physical information and noise. The informative component of the time series is used for the calculation of the Hurst exponent, the Information Length and the Dynamic Time. Based on these measures the physical properties of the time series is revealed., Comment: 4 pages, Conference paper EPS 2022

While reinforcement learning has shown experimental success in a number of applications, it is known to be sensitive to noise and perturbations in the parameters of the system, leading to high variance in the total reward amongst different episodes in slightly different environments. To introduce robustness, as well as sample efficiency, risk-sensitive reinforcement learning methods are being thoroughly studied. In this work, we provide a definition of robust reinforcement learning policies and formulate a risk-sensitive reinforcement learning problem to approximate them, by solving an optimization problem with respect to a modified objective based on exponential criteria. In particular, we study a model-free risk-sensitive variation of the widely-used Monte Carlo Policy Gradient algorithm and introduce a novel risk-sensitive online Actor-Critic algorithm based on solving a multiplicative Bellman equation using stochastic approximation updates. Analytical results suggest that the use of exponential criteria generalizes commonly used ad-hoc regularization approaches, improves sample efficiency, and introduces robustness with respect to perturbations in the model parameters and the environment. The implementation, performance, and robustness properties of the proposed methods are evaluated in simulated experiments.

Hierarchical learning algorithms that gradually approximate a solution to a data-driven optimization problem are essential to decision-making systems, especially under limitations on time and computational resources. In this study, we introduce a general-purpose hierarchical learning architecture that is based on the progressive partitioning of a possibly multi-resolution data space. The optimal partition is gradually approximated by solving a sequence of optimization sub-problems that yield a sequence of partitions with increasing number of subsets. We show that the solution of each optimization problem can be estimated online using gradient-free stochastic approximation updates. As a consequence, a function approximation problem can be defined within each subset of the partition and solved using the theory of two-timescale stochastic approximation algorithms. This simulates an annealing process and defines a robust and interpretable heuristic method to gradually increase the complexity of the learning architecture in a task-agnostic manner, giving emphasis to regions of the data space that are considered more important according to a predefined criterion. Finally, by imposing a tree structure in the progression of the partitions, we provide a means to incorporate potential multi-resolution structure of the data space into this approach, significantly reducing its complexity, while introducing hierarchical variable-rate feature extraction properties similar to certain classes of deep learning architectures. Asymptotic convergence analysis and experimental results are provided for supervised and unsupervised learning problems.

The reliability of the results of network meta-analysis (NMA) lies in the plausibility of key assumption of transitivity. This assumption implies that the effect modifiers' distribution is similar across treatment comparisons. Transitivity is statistically manifested through the consistency assumption which suggests that direct and indirect evidence are in agreement. Several methods have been suggested to evaluate consistency. A popular approach suggests adding inconsistency factors to the NMA model. We follow a different direction by describing each inconsistency factor with a candidate covariate whose choice relies on variable selection techniques. Our proposed method, Stochastic Search Inconsistency Factor Selection (SSIFS), evaluates the consistency assumption both locally and globally, by applying the stochastic search variable selection method to determine whether the inconsistency factors should be included in the model. The posterior inclusion probability of each inconsistency factor quantifies how likely is a specific comparison to be inconsistent. We use posterior model odds or the median probability model to decide on the importance of inconsistency factors. Differences between direct and indirect evidence can be incorporated into the inconsistency detection process. A key point of our proposed approach is the construction of a reasonable "informative" prior concerning network consistency. The prior is based on the elicitation of information derived historical data from 201 published network meta-analyses. The performance of our proposed method is evaluated in two published network meta-analyses. The proposed methodology is publicly available in an R package called ssifs, developed and maintained by the authors of this work.

In this work, we introduce a learning model designed to meet the needs of applications in which computational resources are limited, and robustness and interpretability are prioritized. Learning problems can be formulated as constrained stochastic optimization problems, with the constraints originating mainly from model assumptions that define a trade-off between complexity and performance. This trade-off is closely related to over-fitting, generalization capacity, and robustness to noise and adversarial attacks, and depends on both the structure and complexity of the model, as well as the properties of the optimization methods used. We develop an online prototype-based learning algorithm based on annealing optimization that is formulated as an online gradient-free stochastic approximation algorithm. The learning model can be viewed as an interpretable and progressively growing competitive-learning neural network model to be used for supervised, unsupervised, and reinforcement learning. The annealing nature of the algorithm contributes to minimal hyper-parameter tuning requirements, poor local minima prevention, and robustness with respect to the initial conditions. At the same time, it provides online control over the performance-complexity trade-off by progressively increasing the complexity of the learning model as needed, through an intuitive bifurcation phenomenon. Finally, the use of stochastic approximation enables the study of the convergence of the learning algorithm through mathematical tools from dynamical systems and control, and allows for its integration with reinforcement learning algorithms, constructing an adaptive state-action aggregation scheme., Comment: arXiv admin note: text overlap with arXiv:2102.05836

We consider the problem of understanding the coordinated movements of biological or artificial swarms. In this regard, we propose a learning scheme to estimate the coordination laws of the interacting agents from observations of the swarm's density over time. We describe the dynamics of the swarm based on pairwise interactions according to a Cucker-Smale flocking model, and express the swarm's density evolution as the solution to a system of mean-field hydrodynamic equations. We propose a new family of parametric functions to model the pairwise interactions, which allows for the mean-field macroscopic system of integro-differential equations to be efficiently solved as an augmented system of PDEs. Finally, we incorporate the augmented system in an iterative optimization scheme to learn the dynamics of the interacting agents from observations of the swarm's density evolution over time. The results of this work can offer an alternative approach to study how animal flocks coordinate, create new control schemes for large networked systems, and serve as a central part of defense mechanisms against adversarial drone attacks.

The existence of a universal learning architecture in human cognition is a widely spread conjecture supported by experimental findings from neuroscience. While no low-level implementation can be specified yet, an abstract outline of human perception and learning is believed to entail three basic properties: (a) hierarchical attention and processing, (b) memory-based knowledge representation, and (c) progressive learning and knowledge compaction. We approach the design of such a learning architecture from a system-theoretic viewpoint, developing a closed-loop system with three main components: (i) a multi-resolution analysis pre-processor, (ii) a group-invariant feature extractor, and (iii) a progressive knowledge-based learning module. Multi-resolution feedback loops are used for learning, i.e., for adapting the system parameters to online observations. To design (i) and (ii), we build upon the established theory of wavelet-based multi-resolution analysis and the properties of group convolution operators. Regarding (iii), we introduce a novel learning algorithm that constructs progressively growing knowledge representations in multiple resolutions. The proposed algorithm is an extension of the Online Deterministic Annealing (ODA) algorithm based on annealing optimization, solved using gradient-free stochastic approximation. ODA has inherent robustness and regularization properties and provides a means to progressively increase the complexity of the learning model i.e. the number of the neurons, as needed, through an intuitive bifurcation phenomenon. The proposed multi-resolution approach is hierarchical, progressive, knowledge-based, and interpretable. We illustrate the properties of the proposed architecture in the context of the state-of-the-art learning algorithms and deep learning methods., Comment: arXiv admin note: text overlap with arXiv:2102.05836