Approximate Bayesian computation (ABC) is a powerful and elegant framework for performing inference in simulation-based models. However, due to the difficulty in scaling likelihood estimates, ABC remains useful for relatively low-dimensional problems. We introduce Hamiltonian ABC (HABC), a set of likelihood-free algorithms that apply recent advances in scaling Bayesian learning using Hamiltonian Monte Carlo (HMC) and stochastic gradients. We find that a small number forward simulations can effectively approximate the ABC gradient, allowing Hamiltonian dynamics to efficiently traverse parameter spaces. We also describe a new simple yet general approach of incorporating random seeds into the state of the Markov chain, further reducing the random walk behavior of HABC. We demonstrate HABC on several typical ABC problems, and show that HABC samples comparably to regular Bayesian inference using true gradients on a high-dimensional problem from machine learning.

Many machine learning tasks can be formulated in terms of predicting structured outputs. In frameworks such as the structured support vector machine (SVM-Struct) and the structured perceptron, discriminative functions are learned by iteratively applying efficient maximum a posteriori (MAP) decoding. However, maximum likelihood estimation (MLE) of probabilistic models over these same structured spaces requires computing partition functions, which is generally intractable. This paper presents a method for learning discrete exponential family models using the Bethe approximation to the MLE. Remarkably, this problem also reduces to iterative (MAP) decoding. This connection emerges by combining the Bethe approximation with a Frank-Wolfe (FW) algorithm on a convex dual objective which circumvents the intractable partition function. The result is a new single loop algorithm MLE-Struct, which is substantially more efficient than previous double-loop methods for approximate maximum likelihood estimation. Our algorithm outperforms existing methods in experiments involving image segmentation, matching problems from vision, and a new dataset of university roommate assignments.

We consider an autonomous agent facing a partially observable, stochastic, multiagent environment where the unknown policies of other agents are represented as finite state controllers (FSCs). We show how an agent can (i) learn the FSCs of the other agents, and (ii) exploit these models during interactions. To separate the issues of off-line versus on-line learning we consider here an off-line two-phase approach. During the first phase the agent observes as the other player(s) are interacting with the environment (the observations may be imperfect and the learning agent is not taking part in the interaction.) The collected data is used to learn an ensemble of FSCs that explain the behavior of the other agent(s) using a Bayesian non-parametric (BNP) approach. We verify the quality of the learned models during the second phase by allowing the agent to compute its own optimal policy and interact with the observed agent. The optimal policy for the learning agent is obtained by solving an interactive POMDP in which the states are augmented by the other agent(s)' possible FSCs. The advantage of using the Bayesian nonparametric approach in the first phase is that the complexity (number of nodes) of the learned controllers is not bounded a priori. Our two-phase approach is preliminary and separates the learning using BNP from the complexities of learning on-line while the other agent may be modifying its policy (on-line approach is subject of our future work.) We describe our implementation and results in a multiagent Tiger domain. Our results show that learning improves the agent's performance, which increases with the amount of data collected during the learning phase.

Maintaining an accurate set of beliefs in a partially observable scenario, particularly with respect to other agents operating in the same space, is a vital aspect of multiagent planning. We analyze how the beliefs of an agent can be updated for fast adaptivity to changes in the behavior of an unknown teammate. The main contribution of this paper is the empirical evaluation of an agent cooperating with a teammate whose goals change periodically. We test our approach in a collaborative multiagent domain where identification of goals is necessary for successful completion. The belief revision technique we propose outperforms the traditional approach in a majority of test cases. Additionally, our results suggest the ability to approximate a higher level model by utilizing a belief distribution over a set of lower level behaviors, particularly when the belief update strategy identifies changes in the behavior in a responsive manner.

While great strides have been made in collecting presence data and developing accurate species distribution models, much less is known about the migratory process that guides the spatio-temporal changes in distributions for migrating species, especially birds. In this work, we address a challenging inference task, where given only aggregate and noisy data of the volume of birds for each spatial pixel and time window, we predict the likely transition links with their associated probabilities. We propose a framework to build such migration networks for different bird species and present a real world example of constructing a network using our approach.

Homeless youth are prone to Human Immunodeficiency Virus (HIV) due to their engagement in high risk behavior such as unprotected sex, sex under influence of drugs, etc. Many non-profit agencies conduct interventions to educate and train a select group of homeless youth about HIV prevention and treatment practices and rely on word-of-mouth spread of information through their social network. Previous work in strategic selection of intervention participants does not handle uncertainties in the social network's structure and evolving network state, potentially causing significant shortcomings in spread of information. Thus, we developed PSINET, a decision support system to aid the agencies in this task. PSINET includes the following key novelties: (i) it handles uncertainties in network structure and evolving network state; (ii) it addresses these uncertainties by using POMDPs in influence maximization; and (iii) it provides algorithmic advances to allow high quality approximate solutions for such POMDPs. Simulations show that PSINET achieves around 60% more information spread over the current state-of-the-art. PSINET was developed in collaboration with My Friend's Place (a drop-in agency serving homeless youth in Los Angeles) and is currently being reviewed by their officials.

This paper presents a novel approach to modeling the dynamics of human movements with a grid-based representation.For each grid cell, we formulate the local dynamics using a variant of the left-to-right HMM, and thus explicitly model the exiting direction from the current cell. The dependency of this process on the entry direction is captured by employing the Input-Output HMM (IOHMM). On a higher level, we introduce the place where the whole trajectory originated into the IOHMM framework forming a hierarchical input structure. Therefore, we manage to capture both local spatial-temporal correlations and the long-term dependency on faraway initiating events, thus enabling the developed model to incorporate more information and to generate more informative predictions of future trajectories.The experimental results in an office corridor environment verify the capabilities of our method.

Inspired by recent successes of deep learning in computer vision and speech recognition, we propose a novel framework to encode time series data as different types of images, namely, Gramian Angular Fields (GAF) and Markov Transition Fields (MTF). This enables the use of techniques from computer vision for classification. Using a polar coordinate system, GAF images are represented as a Gramian matrix where each element is the trigonometric sum (i.e., superposition of directions) between different time intervals. MTF images represent the first order Markov transition probability along one dimension and temporal dependency along the other. We used Tiled Convolutional Neural Networks (tiled CNNs) on 12 standard datasets to learn high-level features from individual GAF, MTF, and GAF-MTF images that resulted from combining GAF and MTF representations into a single image. The classification results of our approach are competitive with five stateof-the-art approaches. An analysis of the features and weights learned via tiled CNNs explains why the approach works.

We motivate and develop an additive autoregressive hidden Markov model specifically designed to work on the task of energy disaggregation; that is, separating a whole-building electricity signal into its component device signals whose sum is the aggregate signal observed by a smart meter. This model assumes each device in the building operates as an individual autoregressive HMM, where hidden states represent the underlying power mode of the device and Gaussian emissions correspond to that device's power consumption. The additive property models the observed output (whole-building power signal) as the sum of the emissions of multiple hidden states (i.e., as the sum of individual consumptions of multiple devices in the building). The autoregressive property realistically models how many appliances consume energy and is a new extension to previous work using factorial HMMs for energy disaggregation. Finally, our model also includes a robust mixture component, via an L1-regularized noise term, that can absorb outliers arising in this setting from unknown or rarely-used devices. We extract the power signals and underlying state sequences of single devices in a stagewise fashion and illustrate the results of this process on the Reference Energy Disaggregation Dataset (REDD).

Reducing an automobile's energy consumption will lower its dependency on fossil fuel and extend the travel range of electric vehicles. Automobile Climate Control Systems (CCS) are known to be heavy energy consumers. To help reduce CCS energy consumption, this paper presents an adaptive automated agent, MDP Agent for Climate control Systems -- MACS, which provides drivers advice as to how to set their CCS. First, we present a model which has 78% accuracy in predicting drivers' reactions to different advice in different situations. Using the prediction model, we designed a Markov Decision Process which solution provided the advising policy for MACS. Through empirical evaluation using an electric car, with 83 human subjects, we show that MACS successfully reduced the energy consumption of the subjects by 33% compared to subjects who were not equipped with MACS. MACS also outperformed the state-of-the-art Social agent for Advice Provision (SAP).