In this paper, we propose Barrier Hamiltonian Monte Carlo (BHMC), a version of HMC which aims at sampling from a Gibbs distribution $\pi$ on a manifold $\mathsf{M}$, endowed with a Hessian metric $\mathfrak{g}$ derived from a self-concordant barrier. Like Riemannian Manifold HMC, our method relies on Hamiltonian dynamics which comprise $\mathfrak{g}$. It incorporates the constraints defining $\mathsf{M}$ and is therefore able to exploit its underlying geometry. We first introduce c-BHMC (continuous BHMC), for which we assume that the Hamiltonian dynamics can be integrated exactly, and show that it generates a Markov chain for which $\pi$ is invariant. Secondly, we design n-BHMC (numerical BHMC), a Metropolis-Hastings algorithm which combines an acceptance filter including a "reverse integration check" and numerical integrators of the Hamiltonian dynamics. Our main results establish that n-BHMC generates a reversible Markov chain with respect to $\pi$. This is in contrast to existing algorithms which extend the HMC method to Riemannian manifolds, as they do not deal with asymptotic bias. Our conclusions are supported by numerical experiments where we consider target distributions defined on polytopes.
相關內容
Autonomous driving has a natural bi-level structure. The goal of the upper behavioural layer is to provide appropriate lane change, speeding up, and braking decisions to optimize a given driving task. However, this layer can only indirectly influence the driving efficiency through the lower-level trajectory planner, which takes in the behavioural inputs to produce motion commands. Existing sampling-based approaches do not fully exploit the strong coupling between the behavioural and planning layer. On the other hand, end-to-end Reinforcement Learning (RL) can learn a behavioural layer while incorporating feedback from the lower-level planner. However, purely data-driven approaches often fail in safety metrics in unseen environments. This paper presents a novel alternative; a parameterized bi-level optimization that jointly computes the optimal behavioural decisions and the resulting downstream trajectory. Our approach runs in real-time using a custom GPU-accelerated batch optimizer, and a Conditional Variational Autoencoder learnt warm-start strategy. Extensive simulations show that our approach outperforms state-of-the-art model predictive control and RL approaches in terms of collision rate while being competitive in driving efficiency.
Referred to as the third rung of the causal inference ladder, counterfactual queries typically ask the "What if ?" question retrospectively. The standard approach to estimate counterfactuals resides in using a structural equation model that accurately reflects the underlying data generating process. However, such models are seldom available in practice and one usually wishes to infer them from observational data alone. Unfortunately, the correct structural equation model is in general not identifiable from the observed factual distribution. Nevertheless, in this work, we show that under the assumption that the main latent contributors to the treatment responses are categorical, the counterfactuals can be still reliably predicted. Building upon this assumption, we introduce CounterFactual Query Prediction (CFQP), a novel method to infer counterfactuals from continuous observations when the background variables are categorical. We show that our method significantly outperforms previously available deep-learning-based counterfactual methods, both theoretically and empirically on time series and image data. Our code is available at //github.com/edebrouwer/cfqp.
Recent studies to learn physical laws via deep learning attempt to find the shared representation of the given system by introducing physics priors or inductive biases to the neural network. However, most of these approaches tackle the problem in a system-specific manner, in which one neural network trained to one particular physical system cannot be easily adapted to another system governed by a different physical law. In this work, we use a meta-learning algorithm to identify the general manifold in neural networks that represents Hamilton's equation. We meta-trained the model with the dataset composed of five dynamical systems each governed by different physical laws. We show that with only a few gradient steps, the meta-trained model adapts well to the physical system which was unseen during the meta-training phase. Our results suggest that the meta-trained model can craft the representation of Hamilton's equation in neural networks which is shared across various dynamical systems with each governed by different physical laws.
We study the bias of classical quantile regression and instrumental variable quantile regression estimators. While being asymptotically first-order unbiased, these estimators can have non-negligible second-order biases. We derive a higher-order stochastic expansion of these estimators using empirical process theory. Based on this expansion, we derive an explicit formula for the second-order bias and propose a feasible bias correction procedure that uses finite-difference estimators of the bias components. The proposed bias correction method performs well in simulations. We provide an empirical illustration using Engel's classical data on household expenditure.
(Simplified Abstract) To accomplish breakthroughs in dynamic whole-body locomotion, legged robots have to be terrain aware. Terrain-Aware Locomotion (TAL) implies that the robot can perceive the terrain with its sensors, and can take decisions based on this information. This thesis presents TAL strategies both from a proprioceptive and an exteroceptive perspective. The strategies are implemented at the level of locomotion planning, control, and state estimation, and using optimization and learning techniques. The first part is on TAL strategies at the Whole-Body Control (WBC) level. We introduce a passive WBC (pWBC) framework that allows the robot to stabilize and walk over challenging terrain while taking into account the terrain geometry (inclination) and friction properties. The pWBC relies on rigid contact assumptions which makes it suitable only for stiff terrain. As a consequence, we introduce Soft Terrain Adaptation aNd Compliance Estimation (STANCE) which is a soft terrain adaptation algorithm that generalizes beyond rigid terrain. The second part of the thesis focuses on vision-based TAL strategies. We present Vision-Based Terrain-Aware Locomotion (ViTAL) which is an online planning strategy that selects the footholds based on the robot capabilities, and the robot pose that maximizes the chances of the robot succeeding in reaching these footholds. ViTAL relies on a set of robot skills that characterizes the capabilities of the robot and its legs. The skills include the robot's ability to assess the terrain's geometry, avoid leg collisions, and avoid reaching kinematic limits. Our strategies are based on optimization and learning methods and are validated on HyQ and HyQReal in simulation and experiment. We show that with the help of these strategies, we can push dynamic legged robots one step closer to being fully autonomous and terrain aware.
Splitting schemes are numerical integrators for Hamiltonian problems that may advantageously replace the St\"ormer-Verlet method within Hamiltonian Monte Carlo (HMC) methodology. However, HMC performance is very sensitive to the step size parameter; in this paper we propose a new method in the one-parameter family of second-order of splitting procedures that uses a well-fitting parameter that nullifies the expectation of the energy error for univariate and multivariate Gaussian distributions, taken as a problem-guide for more realistic situations; we also provide a new algorithm that through an adaptive choice of the $b$ parameter and the step-size ensures high sampling performance of HMC. For similar methods introduced in recent literature, by using the proposed step size selection, the splitting integration within HMC method never rejects a sample when applied to univariate and multivariate Gaussian distributions. For more general non Gaussian target distributions the proposed approach exceeds the principal especially when the adaptive choice is used. The effectiveness of the proposed is firstly tested on some benchmarks examples taken from literature. Then, we conduct experiments by considering as target distribution, the Log-Gaussian Cox process and Bayesian Logistic Regression.
This paper makes 3 contributions. First, it generalizes the Lindeberg\textendash Feller and Lyapunov Central Limit Theorems to Hilbert Spaces by way of $L^2$. Second, it generalizes these results to spaces in which sample failure and missingness can occur. Finally, it shows that satisfaction of the Lindeberg\textendash Feller and Lyapunov Conditions in such spaces implies the satisfaction of the conditions in the completely observed space, and how this guarantees the consistency of inferences from the partial functional data. These latter two results are especially important given the increasing attention to statistical inference with partially observed functional data. This paper goes beyond previous research by providing simple boundedness conditions which guarantee that \textit{all} inferences, as opposed to some proper subset of them, will be consistently estimated. This is shown primarily by aggregating conditional expectations with respect to the space of missingness patterns. This paper appears to be the first to apply this technique.
We consider the constrained sampling problem where the goal is to sample from a distribution $\pi(x)\propto e^{-f(x)}$ and $x$ is constrained on a convex body $\mathcal{C}\subset \mathbb{R}^d$. Motivated by penalty methods from optimization, we propose penalized Langevin Dynamics (PLD) and penalized Hamiltonian Monte Carlo (PHMC) that convert the constrained sampling problem into an unconstrained one by introducing a penalty function for constraint violations. When $f$ is smooth and the gradient is available, we show $\tilde{\mathcal{O}}(d/\varepsilon^{10})$ iteration complexity for PLD to sample the target up to an $\varepsilon$-error where the error is measured in terms of the total variation distance and $\tilde{\mathcal{O}}(\cdot)$ hides some logarithmic factors. For PHMC, we improve this result to $\tilde{\mathcal{O}}(\sqrt{d}/\varepsilon^{7})$ when the Hessian of $f$ is Lipschitz and the boundary of $\mathcal{C}$ is sufficiently smooth. To our knowledge, these are the first convergence rate results for Hamiltonian Monte Carlo methods in the constrained sampling setting that can handle non-convex $f$ and can provide guarantees with the best dimension dependency among existing methods with deterministic gradients. We then consider the setting where unbiased stochastic gradients are available. We propose PSGLD and PSGHMC that can handle stochastic gradients without Metropolis-Hasting correction steps. When $f$ is strongly convex and smooth, we obtain an iteration complexity of $\tilde{\mathcal{O}}(d/\varepsilon^{18})$ and $\tilde{\mathcal{O}}(d\sqrt{d}/\varepsilon^{39})$ respectively in the 2-Wasserstein distance. For the more general case, when $f$ is smooth and non-convex, we also provide finite-time performance bounds and iteration complexity results. Finally, we test our algorithms on Bayesian LASSO regression and Bayesian constrained deep learning problems.
In this paper, we study the localization problem in dense urban settings. In such environments, Global Navigation Satellite Systems fail to provide good accuracy due to low likelihood of line-of-sight (LOS) links between the receiver (Rx) to be located and the satellites, due to the presence of obstacles like the buildings. Thus, one has to resort to other technologies, which can reliably operate under non-line-of-sight (NLOS) conditions. Recently, we proposed a Received Signal Strength (RSS) fingerprint and convolutional neural network-based algorithm, LocUNet, and demonstrated its state-of-the-art localization performance with respect to the widely adopted k-nearest neighbors (kNN) algorithm, and to state-of-the-art time of arrival (ToA) ranging-based methods. In the current work, we first recognize LocUNet's ability to learn the underlying prior distribution of the Rx position or Rx and transmitter (Tx) association preferences from the training data, and attribute its high performance to these. Conversely, we demonstrate that classical methods based on probabilistic approach, can greatly benefit from an appropriate incorporation of such prior information. Our studies also numerically prove LocUNet's close to optimal performance in many settings, by comparing it with the theoretically optimal formulations.
Causal discovery and causal reasoning are classically treated as separate and consecutive tasks: one first infers the causal graph, and then uses it to estimate causal effects of interventions. However, such a two-stage approach is uneconomical, especially in terms of actively collected interventional data, since the causal query of interest may not require a fully-specified causal model. From a Bayesian perspective, it is also unnatural, since a causal query (e.g., the causal graph or some causal effect) can be viewed as a latent quantity subject to posterior inference -- other unobserved quantities that are not of direct interest (e.g., the full causal model) ought to be marginalized out in this process and contribute to our epistemic uncertainty. In this work, we propose Active Bayesian Causal Inference (ABCI), a fully-Bayesian active learning framework for integrated causal discovery and reasoning, which jointly infers a posterior over causal models and queries of interest. In our approach to ABCI, we focus on the class of causally-sufficient, nonlinear additive noise models, which we model using Gaussian processes. We sequentially design experiments that are maximally informative about our target causal query, collect the corresponding interventional data, and update our beliefs to choose the next experiment. Through simulations, we demonstrate that our approach is more data-efficient than several baselines that only focus on learning the full causal graph. This allows us to accurately learn downstream causal queries from fewer samples while providing well-calibrated uncertainty estimates for the quantities of interest.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191