We aim to create a framework for transfer learning using latent factor models to learn the dependence structure between a larger source dataset and a target dataset. The methodology is motivated by our goal of building a risk-assessment model for surgery patients, using both institutional and national surgical outcomes data. The national surgical outcomes data is collected through NSQIP (National Surgery Quality Improvement Program), a database housing almost 4 million patients from over 700 different hospitals. We build a latent factor model with a hierarchical prior on the loadings matrix to appropriately account for the different covariance structure in our data. We extend this model to handle more complex relationships between the populations by deriving a scale mixture formulation using stick-breaking properties. Our model provides a transfer learning framework that utilizes all information from both the source and target data, while modeling the underlying inherent differences between them.

Due to physiological variation, patients diagnosed with the same condition may exhibit divergent, but related, responses to the same treatments. Hidden Parameter Markov Decision Processes (HiP-MDPs) tackle this transfer-learning problem by embedding these tasks into a low-dimensional space. However, the original formulation of HiP-MDP had a critical flaw: the embedding uncertainty was modelled independently of the agent's state uncertainty, requiring an unnatural training procedure in which all tasks visited every part of the state space--possible for robots that can be moved to a particular location, impossible for human patients. We update the HiP-MDP framework and extend it to more robustly develop personalized medicine strategies for HIV treatment.

Student-$t$ processes have recently been proposed as an appealing alternative non-parameteric function prior. They feature enhanced flexibility and predictive variance. In this work the use of Student-$t$ processes are explored for multi-objective Bayesian optimization. In particular, an analytical expression for the hypervolume-based probability of improvement is developed for independent Student-$t$ process priors of the objectives. Its effectiveness is shown on a multi-objective optimization problem which is known to be difficult with traditional Gaussian processes.

Smart phone apps that enable users to easily track their diets have become widespread in the last decade. This has created an opportunity to discover new insights into obesity and weight loss by analyzing the eating habits of the users of such apps. In this paper, we present diet2vec: an approach to modeling latent structure in a massive database of electronic diet journals. Through an iterative contract-and-expand process, our model learns real-valued embeddings of users' diets, as well as embeddings for individual foods and meals. We demonstrate the effectiveness of our approach on a real dataset of 55K users of the popular diet-tracking app LoseIt\footnote{http://www.loseit.com/}. To the best of our knowledge, this is the largest fine-grained diet tracking study in the history of nutrition and obesity research. Our results suggest that diet2vec finds interpretable results at all levels, discovering intuitive representations of foods, meals, and diets.

We present an optimizer which uses Bayesian optimization to tune the system parameters of distributed stochastic gradient descent (SGD). Given a specific context, our goal is to quickly find efficient configurations which appropriately balance the load between the available machines to minimize the average SGD iteration time. Our experiments consider setups with over thirty parameters. Traditional Bayesian optimization, which uses a Gaussian process as its model, is not well suited to such high dimensional domains. To reduce convergence time, we exploit the available structure. We design a probabilistic model which simulates the behavior of distributed SGD and use it within Bayesian optimization. Our model can exploit many runtime measurements for inference per evaluation of the objective function. Our experiments show that our resulting optimizer converges to efficient configurations within ten iterations, the optimized configurations outperform those found by generic optimizer in thirty iterations by up to 2X.

A number of recent approaches to policy learning in 2D game domains have been successful going directly from raw input images to actions. However when employed in complex 3D environments, they typically suffer from challenges related to partial observability, combinatorial exploration spaces, path planning, and a scarcity of rewarding scenarios. Inspired from prior work in human cognition that indicates how humans employ a variety of semantic concepts and abstractions (object categories, localisation, etc.) to reason about the world, we build an agent-model that incorporates such abstractions into its policy-learning framework. We augment the raw image input to a Deep Q-Learning Network (DQN), by adding details of objects and structural elements encountered, along with the agent's localisation. The different components are automatically extracted and composed into a topological representation using on-the-fly object detection and 3D-scene reconstruction. We evaluate the efficacy of our approach in "Doom", a 3D first-person combat game that exhibits a number of challenges discussed, and show that our augmented framework consistently learns better, more effective policies.

Humans have been manually extracting patterns from data for centuries, but the increasing volume of data in modern times has called for more automated approaches. Information leads to power and success, and thanks to sophisticated technologies such as computers, satellites, etc., we have been collecting tremendous amounts of information. Initially, with the advent of computers and means for mass digital storage, we started collecting and storing all sorts of data, counting on the power of computers to help sort through this amalgam of information. Unfortunately, these massive collections of data stored on disparate structures very rapidly became overwhelming. A variety of information collected in digital form in databases and in flat files.

We consider the problem of non-parametric regression with a potentially large number of covariates. We propose a convex, penalized estimation framework that is particularly well-suited for high-dimensional sparse additive models. The proposed approach combines appealing features of finite basis representation and smoothing penalties for non-parametric estimation. In particular, in the case of additive models, a finite basis representation provides a parsimonious representation for fitted functions but is not adaptive when component functions posses different levels of complexity. On the other hand, a smoothing spline type penalty on the component functions is adaptive but does not offer a parsimonious representation of the estimated function. The proposed approach simultaneously achieves parsimony and adaptivity in a computationally efficient framework. We demonstrate these properties through empirical studies on both real and simulated datasets. We show that our estimator converges at the minimax rate for functions within a hierarchical class. We further establish minimax rates for a large class of sparse additive models. The proposed method is implemented using an efficient algorithm that scales similarly to the Lasso with the number of covariates and samples size.

We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our first contribution is a complexity measure, the Bellman rank, that we show enables tractable learning of near-optimal behavior in these processes and is naturally small for many well-studied reinforcement learning settings. Our second contribution is a new reinforcement learning algorithm that engages in systematic exploration to learn contextual decision processes with low Bellman rank. Our algorithm provably learns near-optimal behavior with a number of samples that is polynomial in all relevant parameters but independent of the number of unique observations. The approach uses Bellman error minimization with optimistic exploration and provides new insights into efficient exploration for reinforcement learning with function approximation.

Datasets containing large samples of time-to-event data arising from several small heterogeneous groups are commonly encountered in statistics. This presents problems as they cannot be pooled directly due to their heterogeneity or analyzed individually because of their small sample size. Bayesian nonparametric modelling approaches can be used to model such datasets given their ability to flexibly share information across groups. In this paper, we will compare three popular Bayesian nonparametric methods for modelling the survival functions of heterogeneous groups. Specifically, we will first compare the modelling accuracy of the Dirichlet process, the hierarchical Dirichlet process, and the nested Dirichlet process on simulated datasets of different sizes, where group survival curves differ in shape or in expectation. We, then, will compare the models on a real-world injury dataset.