We propose extreme stochastic variational inference (ESVI), an asynchronous and lock-free algorithm to perform variational inference on massive real world datasets. Stochastic variational inference (SVI), the state-of-the-art algorithm for scaling variational inference to large-datasets, is inherently serial. Moreover, it requires the parameters to fit in the memory of a single processor; this is problematic when the number of parameters is in billions. ESVI overcomes these limitations by requiring that each processor only access a subset of the data and a subset of the parameters, thus providing data and model parallelism simultaneously. We demonstrate the effectiveness of ESVI by running Latent Dirichlet Allocation (LDA) on UMBC-3B, a dataset that has a vocabulary of 3 million and a token size of 3 billion. To best of our knowledge, this is an order of magnitude larger than the largest dataset on which results using variational inference have been reported in literature. In our experiments, we found that ESVI outperforms VI and SVI, and also achieves a better quality solution. In addition, we propose a strategy to speed up computation and save memory when fitting large number of topics.

Learning from expert demonstrations has received a lot of attention in artificial intelligence and machine learning. The goal is to infer the underlying reward function that an agent is optimizing given a set of observations of the agent's behavior over time in a variety of circumstances, the system state trajectories, and a plant model specifying the evolution of the system state for different agent's actions. The system is often modeled as a Markov decision process, that is, the next state depends only on the current state and agent's action, and the the agent's choice of action depends only on the current state. While the former is a Markovian assumption on the evolution of system state, the later assumes that the target reward function is itself Markovian. In this work, we explore learning a class of non-Markovian reward functions, known in the formal methods literature as specifications. These specifications offer better composition, transferability, and interpretability. We then show that inferring the specification can be done efficiently without unrolling the transition system. We demonstrate on a 2-d grid world example.

During their first years of life, infants learn the language(s) of their environment at an amazing speed despite large cross cultural variations in amount and complexity of the available language input. Understanding this simple fact still escapes current cognitive and linguistic theories. Recently, spectacular progress in the engineering science, notably, machine learning and wearable technology, offer the promise of revolutionizing the study of cognitive development. Machine learning offers powerful learning algorithms that can achieve human-like performance on many linguistic tasks. Wearable sensors can capture vast amounts of data, which enable the reconstruction of the sensory experience of infants in their natural environment. The project of 'reverse engineering' language development, i.e., of building an effective system that mimics infant's achievements appears therefore to be within reach. Here, we analyze the conditions under which such a project can contribute to our scientific understanding of early language development. We argue that instead of defining a sub-problem or simplifying the data, computational models should address the full complexity of the learning situation, and take as input the raw sensory signals available to infants. This implies that (1) accessible but privacy-preserving repositories of home data be setup and widely shared, and (2) models be evaluated at different linguistic levels through a benchmark of psycholinguist tests that can be passed by machines and humans alike, (3) linguistically and psychologically plausible learning architectures be scaled up to real data using probabilistic/optimization principles from machine learning. We discuss the feasibility of this approach and present preliminary results.

Two fundamental problems in unsupervised learning are efficient inference for latent-variable models and robust density estimation based on large amounts of unlabeled data. Algorithms for the two tasks, such as normalizing flows and generative adversarial networks (GANs), are often developed independently. In this paper, we propose the concept of {\em continuous-time flows} (CTFs), a family of diffusion-based methods that are able to asymptotically approach a target distribution. Distinct from normalizing flows and GANs, CTFs can be adopted to achieve the above two goals in one framework, with theoretical guarantees. Our framework includes distilling knowledge from a CTF for efficient inference, and learning an explicit energy-based distribution with CTFs for density estimation. Both tasks rely on a new technique for distribution matching within amortized learning. Experiments on various tasks demonstrate promising performance of the proposed CTF framework, compared to related techniques.

Inverse classification uses an induced classifier as a queryable oracle to guide test instances towards a preferred posterior class label. The result produced from the process is a set of instance-specific feature perturbations, or recommendations, that optimally improve the probability of the class label. In this work, we adopt a causal approach to inverse classification, eliciting treatment policies (i.e., feature perturbations) for models induced with causal properties. In so doing, we solve a long-standing problem of eliciting multiple, continuously valued treatment policies, using an updated framework and corresponding set of assumptions, which we term the inverse classification potential outcomes framework (ICPOF), along with a new measure, referred to as the individual future estimated effects ($i$FEE). We also develop the approximate propensity score (APS), based on Gaussian processes, to weight treatments, much like the inverse propensity score weighting used in past works. We demonstrate the viability of our methods on student performance.

We provide a comprehensive overview and tooling for GP modeling with non-Gaussian likelihoods using state space methods. The state space formulation allows for solving one-dimensional GP models in $\mathcal{O}(n)$ time and memory complexity. While existing literature has focused on the connection between GP regression and state space methods, the computational primitives allowing for inference using general likelihoods in combination with the Laplace approximation (LA), variational Bayes (VB), and assumed density filtering (ADF) / expectation propagation (EP) schemes has been largely overlooked. We present means of combining the efficient $\mathcal{O}(n)$ state space methodology with existing inference methods. We also further extend existing methods, and provide unifying code implementing all approaches.

Quadrature is the problem of estimating intractable integrals, a problem that arises in many Bayesian machine learning settings. We present an improved Bayesian framework for estimating intractable integrals of specific kinds of constrained integrands. We derive the necessary approximation scheme for a specific and especially useful instantiation of this framework: the use of a log transformation to model non-negative integrands. We also propose a novel method for optimizing the hyperparameters associated with this framework; we optimize the hyperparameters in the original space of the integrand as opposed to in the transformed space, resulting in a model that better explains the actual data. Experiments on both synthetic and real-world data demonstrate that the proposed framework achieves more-accurate estimates using less wall-clock time than previously preposed Bayesian quadrature procedures for non-negative integrands.

Learning algorithms that aggregate predictions from an ensemble of diverse base classifiers consistently outperform individual methods. Many of these strategies have been developed in a supervised setting, where the accuracy of each base classifier can be empirically measured and this information is incorporated in the training process. However, the reliance on labeled data precludes the application of ensemble methods to many real world problems where labeled data has not been curated. To this end we developed a new theoretical framework for binary classification, the Strategy for Unsupervised Multiple Method Aggregation (SUMMA), to estimate the performances of base classifiers and an optimal strategy for ensemble learning from unlabeled data.

In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks. Under the assumption that future tasks are 'related' to previous tasks, representations should be learned in a way which captures the common structure across learned tasks, while allowing the learner sufficient flexibility to adapt to novel aspects of new tasks. We present a framework for meta-learning that is based on generalization error bounds, allowing us to extend various PAC-Bayes bounds to meta-learning. Learning takes place through the construction of a distribution over hypotheses based on the observed tasks, and its utilization for learning a new task. Thus, prior knowledge is incorporated through setting an experience-dependent prior for novel tasks. We develop a gradient-based algorithm which minimizes an objective function derived from the bounds and demonstrate its effectiveness numerically with deep neural networks. In addition to establishing the improved performance available through meta-learning, we demonstrate the intuitive way by which prior information is manifested at different levels of the network.

Recent work in unsupervised representation learning has focused on learning deep directed latent-variable models. Fitting these models by maximizing the marginal likelihood or evidence is typically intractable, thus a common approximation is to maximize the evidence lower bound (ELBO) instead. However, maximum likelihood training (whether exact or approximate) does not necessarily result in a good latent representation, as we demonstrate both theoretically and empirically. In particular, we derive variational lower and upper bounds on the mutual information between the input and the latent variable, and use these bounds to derive a rate-distortion curve that characterizes the tradeoff between compression and reconstruction accuracy. Using this framework, we demonstrate that there is a family of models with identical ELBO, but different quantitative and qualitative characteristics. Our framework also suggests a simple new method to ensure that latent variable models with powerful stochastic decoders do not ignore their latent code.