Recent advancement in online optimization and control has provided novel tools to study online linear quadratic regulator (LQR) problems, where cost matrices are varying adversarially over time. However, the controller parameterization of existing works may not satisfy practical conditions like sparsity due to physical connections. In this work, we study online linear quadratic Gaussian problems with a given linear constraint imposed on the controller. Inspired by the recent work of [1] which proposed, for a linearly constrained policy optimization of an offline LQR, a second order method equipped with a Riemannian metric that emerges naturally in the context of optimal control problems, we propose online optimistic Newton on manifold (OONM) which provides an online controller based on the prediction on the first and second order information of the function sequence. To quantify the proposed algorithm, we leverage the notion of regret defined as the sub-optimality of its cumulative cost to that of a (locally) minimizing controller sequence and provide the regret bound in terms of the path-length of the minimizer sequence. Simulation results are also provided to verify the property of OONM.
相關內容
This study evaluates the usage of virtual reality (VR) technologies as a teaching tool in oral placement therapy, a subset of speech therapy. The researcher distributed instructional videos using traditional lecture and modified three-dimensional video to prompt responses. Data was gathered with a two-part Google Form: In "Section 1: Knowledge Test" participants were asked to determine how well they received the information displayed to them. In "Section 2: Opinion Test" participants were asked diagnostic and subjective questions via Likert scale ranging from 1 ("Strongly Disagree") to 5 ("Strongly Agree") to determine how well they enjoyed viewing the information displayed to them. Averages for Section 1 were 92.00% for the control group (viewing 2D, unmodified video) and 77.88% for the experimental group (viewing 3D, VR video). Almost all participants answered at least 60% of the questions correctly. Averages for 2D and 3D participants were 4.53/5 and 3.82/5, respectively for "positive" prompts. Exactly 50% of participants experiencing VR video preferred the method to a traditional lecture. This study determines that virtual reality is viable as a learning tool, but knowledge obtained is not necessarily as high as using traditional lecture. Further experimentation is required to determine how well oral placement therapists respond to physically interacting with a model instead of only viewing it. Copies of the Google Form used to collect responses, all raw data, and a flowchart outlining each step used to construct the 3D video can be found in the Appendix.
We reinvigorate maximum likelihood estimation (MLE) for macroeconomic density forecasting through a novel neural network architecture with dedicated mean and variance hemispheres. Our architecture features several key ingredients making MLE work in this context. First, the hemispheres share a common core at the entrance of the network which accommodates for various forms of time variation in the error variance. Second, we introduce a volatility emphasis constraint that breaks mean/variance indeterminacy in this class of overparametrized nonlinear models. Third, we conduct a blocked out-of-bag reality check to curb overfitting in both conditional moments. Fourth, the algorithm utilizes standard deep learning software and thus handles large data sets - both computationally and statistically. Ergo, our Hemisphere Neural Network (HNN) provides proactive volatility forecasts based on leading indicators when it can, and reactive volatility based on the magnitude of previous prediction errors when it must. We evaluate point and density forecasts with an extensive out-of-sample experiment and benchmark against a suite of models ranging from classics to more modern machine learning-based offerings. In all cases, HNN fares well by consistently providing accurate mean/variance forecasts for all targets and horizons. Studying the resulting volatility paths reveals its versatility, while probabilistic forecasting evaluation metrics showcase its enviable reliability. Finally, we also demonstrate how this machinery can be merged with other structured deep learning models by revisiting Goulet Coulombe (2022)'s Neural Phillips Curve.
Integrating Disambiguation and User Preferences into Large Language Models for Robot Motion Planning
This paper presents a framework that can interpret humans' navigation commands containing temporal elements and directly translate their natural language instructions into robot motion planning. Central to our framework is utilizing Large Language Models (LLMs). To enhance the reliability of LLMs in the framework and improve user experience, we propose methods to resolve the ambiguity in natural language instructions and capture user preferences. The process begins with an ambiguity classifier, identifying potential uncertainties in the instructions. Ambiguous statements trigger a GPT-4-based mechanism that generates clarifying questions, incorporating user responses for disambiguation. Also, the framework assesses and records user preferences for non-ambiguous instructions, enhancing future interactions. The last part of this process is the translation of disambiguated instructions into a robot motion plan using Linear Temporal Logic. This paper details the development of this framework and the evaluation of its performance in various test scenarios.
We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data, such as irregular samples, missing data, or unaligned measurements from multiple sensors. Our method relies on a continuous-time-dependent model of the series' evolution dynamics. It leverages adaptations of conditional, implicit neural representations for sequential data. A modulation mechanism, driven by a meta-learning algorithm, allows adaptation to unseen samples and extrapolation beyond observed time-windows for long-term predictions. The model provides a highly flexible and unified framework for imputation and forecasting tasks across a wide range of challenging scenarios. It achieves state-of-the-art performance on classical benchmarks and outperforms alternative time-continuous models.
Large language models (LLMs) have shown impressive effectiveness in various software engineering tasks, including automated program repair (APR). In this study, we take a deep dive into automated bug fixing utilizing LLMs. In contrast to many deep learning-based APR methods that assume known bug locations, rely on line-level localization tools, or address bug prediction and fixing in one step, our approach uniquely employs LLMs to predict bug location at the token level and subsequently utilizes them for bug fixing. This methodological separation of bug localization and fixing using different LLMs enables effective integration of diverse contextual information and improved incorporation of inductive biases. We introduce Toggle: Token-Granulated Bug Localization and Repair, a comprehensive program repair framework that integrates a bug localization model, an adjustment unit, and a bug-fixing model. Toggle takes a buggy function as input and generates a complete corrected function. We investigate various styles of prompting to the bug fixing model to identify the most effective prompts that better utilize the inductive bias and significantly outperform others. Toggle achieves the new state-of-the-art (SOTA) performance on the CodeXGLUE code refinement benchmark, and exhibits better and comparable performance on several other widely-used APR datasets, including Defects4J.
This paper presents a distributed model predictive control (DMPC) algorithm for a heterogeneous platoon using arbitrary communication topologies, as long as each vehicle is able to communicate with a preceding vehicle in the platoon. The proposed DMPC algorithm is able to accommodate any spacing policy that is affine in a vehicle's velocity, which includes constant distance or constant time headway spacing policies. By analyzing the total cost for the entire platoon, a sufficient condition is derived to guarantee platoon asymptotic stability. Simulation experiments with a platoon of 50 vehicles and hardware experiments with a platoon of four 1/10th scale vehicles validate the algorithm and compare performance under different spacing policies and communication topologies.
This paper explores the enhancement of solution diversity in evolutionary algorithms (EAs) for the maximum matching problem, concentrating on complete bipartite graphs and paths. We adopt binary string encoding for matchings and use Hamming distance to measure diversity, aiming for its maximization. Our study centers on the $(\mu+1)$-EA and $2P-EA_D$, which are applied to optimize diversity. We provide a rigorous theoretical and empirical analysis of these algorithms. For complete bipartite graphs, our runtime analysis shows that, with a reasonably small $\mu$, the $(\mu+1)$-EA achieves maximal diversity with an expected runtime of $O(\mu^2 m^4 \log(m))$ for the small gap case (where the population size $\mu$ is less than the difference in the sizes of the bipartite partitions) and $O(\mu^2 m^2 \log(m))$ otherwise. For paths, we establish an upper runtime bound of $O(\mu^3 m^3)$. The $2P-EA_D$ displays stronger performance, with bounds of $O(\mu^2 m^2 \log(m))$ for the small gap case, $O(\mu^2 n^2 \log(n))$ otherwise, and $O(\mu^3 m^2)$ for paths. Here, $n$ represents the total number of vertices and $m$ the number of edges. Our empirical studies, which examine the scaling behavior with respect to $m$ and $\mu$, complement these theoretical insights and suggest potential for further refinement of the runtime bounds.
We provide a preliminary study on utilizing GPU (Graphics Processing Unit) to accelerate computation for three simulation optimization tasks with either first-order or second-order algorithms. Compared to the implementation using only CPU (Central Processing Unit), the GPU implementation benefits from computational advantages of parallel processing for large-scale matrices and vectors operations. Numerical experiments demonstrate computational advantages of utilizing GPU implementation in simulation optimization problems, and show that such advantage comparatively further increase as the problem scale increases.
As soon as abstract mathematical computations were adapted to computation on digital computers, the problem of efficient representation, manipulation, and communication of the numerical values in those computations arose. Strongly related to the problem of numerical representation is the problem of quantization: in what manner should a set of continuous real-valued numbers be distributed over a fixed discrete set of numbers to minimize the number of bits required and also to maximize the accuracy of the attendant computations? This perennial problem of quantization is particularly relevant whenever memory and/or computational resources are severely restricted, and it has come to the forefront in recent years due to the remarkable performance of Neural Network models in computer vision, natural language processing, and related areas. Moving from floating-point representations to low-precision fixed integer values represented in four bits or less holds the potential to reduce the memory footprint and latency by a factor of 16x; and, in fact, reductions of 4x to 8x are often realized in practice in these applications. Thus, it is not surprising that quantization has emerged recently as an important and very active sub-area of research in the efficient implementation of computations associated with Neural Networks. In this article, we survey approaches to the problem of quantizing the numerical values in deep Neural Network computations, covering the advantages/disadvantages of current methods. With this survey and its organization, we hope to have presented a useful snapshot of the current research in quantization for Neural Networks and to have given an intelligent organization to ease the evaluation of future research in this area.
In this paper, we propose a novel Feature Decomposition and Reconstruction Learning (FDRL) method for effective facial expression recognition. We view the expression information as the combination of the shared information (expression similarities) across different expressions and the unique information (expression-specific variations) for each expression. More specifically, FDRL mainly consists of two crucial networks: a Feature Decomposition Network (FDN) and a Feature Reconstruction Network (FRN). In particular, FDN first decomposes the basic features extracted from a backbone network into a set of facial action-aware latent features to model expression similarities. Then, FRN captures the intra-feature and inter-feature relationships for latent features to characterize expression-specific variations, and reconstructs the expression feature. To this end, two modules including an intra-feature relation modeling module and an inter-feature relation modeling module are developed in FRN. Experimental results on both the in-the-lab databases (including CK+, MMI, and Oulu-CASIA) and the in-the-wild databases (including RAF-DB and SFEW) show that the proposed FDRL method consistently achieves higher recognition accuracy than several state-of-the-art methods. This clearly highlights the benefit of feature decomposition and reconstruction for classifying expressions.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191