Neural Information Processing Systems http://nips.cc/

We present computationally efficient algorithms to test various combinatorial structures of large-scale graphical models. In order to test the hypotheses on their topological structures, we propose two adjacency matrix sketching frameworks: neighborhood sketching and subgraph sketching.

Multi-armed bandit (MAB) is a predominant model for characterizing the tradeoff between exploration and exploitation in decision-making problems. Although this is an intrinsic tradeoff in many tasks, some application domains prefer a dedicated exploration procedure in which the goal is to identify an optimal object among a collection of candidates and the reward or loss incurred during exploration is irrelevant. In light of these applications, the related learning problem, called pure exploration in MABs, has received much attention. Recent advances in pure exploration MABs have found potential applications in many domains including crowdsourcing, communication network and online advertising. In many of these application domains, a recurring problem is to identify the optimal object with certain combinatorial structure .

Applying BO with GPs on combinatorial spaces is, therefore, not straightforward.

We study the {\em combinatorial pure exploration (CPE)} problem in the stochastic multi-armed bandit setting, where a learner explores a set of arms with the objective of identifying the optimal member of a \emph{decision class}, which is a collection of subsets of arms with certain combinatorial structures such as size-$K$ subsets, matchings, spanning trees or paths, etc. The CPE problem represents a rich class of pure exploration tasks which covers not only many existing models but also novel cases where the object of interest has a non-trivial combinatorial structure. In this paper, we provide a series of results for the general CPE problem. We present general learning algorithms which work for all decision classes that admit offline maximization oracles in both fixed confidence and fixed budget settings. We prove problem-dependent upper bounds of our algorithms. Our analysis exploits the combinatorial structures of the decision classes and introduces a new analytic tool. We also establish a general problem-dependent lower bound for the CPE problem. Our results show that the proposed algorithms achieve the optimal sample complexity (within logarithmic factors) for many decision classes. In addition, applying our results back to the problems of top-$K$ arms identification and multiple bandit best arms identification, we recover the best available upper bounds up to constant factors and partially resolve a conjecture on the lower bounds.

This assists in analysis and provides a foundation for further research.

Multi-armed bandit (MAB) is a predominant model for characterizing the tradeoff between exploration and exploitation in decision-making problems. Although this is an intrinsic tradeoff in many tasks, some application domains prefer a dedicated exploration procedure in which the goal is to identify an optimal object among a collection of candidates and the reward or loss incurred during exploration is irrelevant. In light of these applications, the related learning problem, called pure exploration in MABs, has received much attention. Recent advances in pure exploration MABs have found potential applications in many domains including crowdsourcing, communication network and online advertising. In many of these application domains, a recurring problem is to identify the optimal object with certain combinatorial structure.

The capability to learn latent representations plays a key role in the effectiveness of recent machine learning methods. An active frontier in representation learning is understanding representations for combinatorial structures which may not admit well-behaved local neighborhoods or distance functions. For example, for polygons, slightly perturbing vertex locations might lead to significant changes in their combinatorial structure (expressed as their triangulation or visibility graph) and may even lead to invalid polygons. In this paper, we investigate representations to capture the underlying combinatorial structures of polygons. Specifically, we study the open problem of Visibility Reconstruction: Given a visibility graph G, construct a polygon P whose visibility graph is G. Visibility Reconstruction belongs to the Existential Theory of Reals ( R) complexity class (which lies between NP and P-SPACE). Currently, reconstruction algorithms are available only for specific polygon classes. Establishing the hardness of the general problem is open. We introduce VisDiff, a novel diffusion-based approach to reconstruct a polygon from its given visibility graph G. Our method first estimates the signed distance function (SDF) of P from G. Afterwards, it extracts ordered vertex locations that have the pairwise visibility relationship given by the edges of G. Our main insight is that going through the SDF significantly improves learning for reconstruction. In order to train VisDiff, we make two main contributions: (1) We design novel loss components for computing the visibility in a differentiable manner and (2) create a carefully curated dataset. We use this dataset to benchmark our method and achieve 21% improvement in F1-Score over standard methods. We also demonstrate effective generalization to out-of-distribution polygon types and show that learning a generative model allows us to sample the set of polygons with a given visibility graph. Finally, we extend our method to the related combinatorial problem of reconstruction from a triangulation.