Relational learning is concerned with predicting unknown values of a relation, given a database of entities and observed relations among entities. An example of relational learning is movie rating prediction, where entities could include users, movies, genres, and actors. Relations would then encode users' ratings of movies, movies' genres, and actors' roles in movies. A common prediction technique given one pairwise relation, for example a #users × #movies ratings matrix, is low-rank matrix factorization. In domains with multiple relations, represented as multiple matrices, we may improve predictive accuracy by exploiting information from one relation while predicting another. To this end, we propose a collective matrix factorization model: we simultaneously factor several matrices, sharing parameters among factors when an entity participates in multiple relations. Each relation can have a different value type and error distribution; so, we allow nonlinear relationships between the parameters and outputs, using Bregman divergences to measure error. We extend standard alternating projection algorithms to our model, and derive an efficient Newton update for the projection. Furthermore, we propose stochastic optimization methods to deal with large, sparse matrices. Our model generalizes several existing matrix factorization methods, and therefore yields new large-scale optimization algorithms for these problems. Our model can handle any pairwise relational schema and a wide variety of error models. We demonstrate its efficiency, as well as the benefit of sharing parameters among relations.

Database management system (DBMS) configuration tuning is an essential aspect of any data-intensive application effort. But this is historically a difficult task because DBMSs have hundreds of configuration "knobs" that control everything in the system, such as the amount of memory to use for caches and how often data is written to storage. The problem with these knobs is that they are not standardized (i.e., two DBMSs use a different name for the same knob), not independent (i.e., changing one knob can impact others), and not universal (i.e., what works for one application may be sub-optimal for another). Worse, information about the effects of the knobs typically comes only from (expensive) experience.To overcome these challenges, we present an automated approach that leverages past experience and collects new information to tune DBMS configurations: we use a combination of supervised and unsupervised machine learning methods to (1) select the most impactful knobs, (2) map unseen database workloads to previous workloads from which we can transfer experience, and (3) recommend knob settings. We implemented our techniques in a new tool called OtterTune and tested it on three DBMSs. Our evaluation shows that OtterTune recommends configurations that are as good as or better than ones generated by existing tools or a human expert.

Relational learning is concerned with predicting unknown values of a relation, given a database of entities and observed relations among entities. An example of relational learning is movie rating prediction, where entities could include users, movies, genres, and actors. Relations would then encode users' ratings of movies, movies' genres, and actors' roles in movies. A common prediction technique given one pairwise relation, for example a #users × #movies ratings matrix, is low-rank matrix factorization. In domains with multiple relations, represented as multiple matrices, we may improve predictive accuracy by exploiting information from one relation while predicting another. To this end, we propose a collective matrix factorization model: we simultaneously factor several matrices, sharing parameters among factors when an entity participates in multiple relations. Each relation can have a different value type and error distribution; so, we allow nonlinear relationships between the parameters and outputs, using Bregman divergences to measure error. We extend standard alternating projection algorithms to our model, and derive an efficient Newton update for the projection. Furthermore, we propose stochastic optimization methods to deal with large, sparse matrices. Our model generalizes several existing matrix factorization methods, and therefore yields new large-scale optimization algorithms for these problems. Our model can handle any pairwise relational schema and a wide variety of error models. We demonstrate its efficiency, as well as the benefit of sharing parameters among relations.

The success of reinforcement learning in practical problems depends on the ability t o c o m bine function approximation with temporal di erence methods such as value iteration. Experiments in this area have produced mixed results; there have been both notable successes and notable disappointments. Theory has been scarce, mostly due to the di culty of reasoning about function approximators that generalize beyond the observed data. We provide a proof of convergence for a wide class of temporal di erence methods involving function approximators such as k-nearest-neighbor, and show experimentally that these methods can be useful. The proof is based on a view of function approximators as expansion or contraction mappings. In addition, we present a novel view of approximate value iteration: an approximate algorithm for one environment turns out to be an exact algorithm for a di erent environment.

The Partially Observable Markov Decision Process has long been recognized as a rich framework for real-world planning and control problems, especially in robotics. However exact solutions in this framework are typically computationally intractable for all but the smallest problems. A well-known technique for speeding up POMDP solving involves performing value backups at specific belief points, rather than over the entire belief simplex. The efficiency of this approach, however, depends greatly on the selection of points. This paper presents a set of novel techniques for selecting informative belief points which work well in practice. The point selection procedure is combined with point-based value backups to form an effective anytime POMDP algorithm called Point-Based Value Iteration (PBVI). The first aim of this paper is to introduce this algorithm and present a theoretical analysis justifying the choice of belief selection technique. The second aim of this paper is to provide a thorough empirical comparison between PBVI and other state-of-the-art POMDP methods, in particular the Perseus algorithm, in an effort to highlight their similarities and differences. Evaluation is performed using both standard POMDP domains and realistic robotic tasks