We realize the half-steps of a general class of Markov chains as alternating projections with respect to the reverse Kullback-Leibler divergence between sets of joint probability distributions which admit an information geometrical property known as autoparallelism. We exhibit both a weak and strong duality between the Markov chains defined by the even and odd half-steps of the alternating projection scheme, which manifests as an equivalence of entropy decay statement regarding the chains, with a precise characterization of the entropy decrease at each half-step. We apply this duality to several Markov chains of interest, and obtain either new results or short, alternative proofs for mixing bounds on the dual chain, with the Swendsen-Wang dynamics serving as a key example. Additionally, we draw parallels between the half-steps of the relevant Markov chains and the Sinkhorn algorithm from the field of entropically regularized optimal transport, which are unified by the perspective of alternating projections with respect to an \alpha-divergence on the probability simplex.

A fundamental approach to semi-supervised learning is to leverage the structure of the sample space to diffuse label information from annotated examples to unlabeled points. Traditional methods model the input data points as a graph and rely on fast algorithms for solving Laplacian systems of equations, such as those defining PageRank. However, previous work has demonstrated that graph-based models fail to capture higher-order relations, such as group membership, which are better modeled by hypergraphs. Unfortunately, the scalable application of hypergraph models has been hampered by the non-linearity of the hypergraph Laplacian. In this paper, we present highly scalable algorithms for hypergraph primitives, such as hypergraph PageRank vectors and hypergraph Laplacian systems, over general families of hypergraphs. In addition to giving strong theoretical guarantees, we empirically showcase the speed of our algorithms on benchmark instances of semi-supervised learning on categorical data. We exploit their generality to improve semi-supervised manifold clustering via hypergraph models. By providing significant speed-ups on fundamental hypergraph tasks, our algorithms enable the deployment of hypergraph models on a massive scale.

In this paper, we address the top-𝐾 ranking problem with a monotone adversary. We consider the scenario where a comparison graph is randomly generated and the adversary is allowed to add arbitrary edges. The statistician’s goal is then to accurately identify the top-𝐾 preferred items based on pairwise comparisons derived from this semi-random comparison graph. The main contribution of this paper is to develop a weighted maximum likelihood estimator (MLE) that achieves near-optimal sample complexity, up to a log2(𝑛) factor, where 𝑛 denotes the number of items under comparison. This is made possible through a combination of analytical and algorithmic innovations. On the analytical front, we provide a refined ℓ∞ error analysis of the weighted MLE that is more explicit and tighter than existing analyses. It relates the ℓ∞ error with the spectral properties of the weighted comparison graph. Motivated by this, our algorithmic innovation involves the development of an SDP-based approach to reweight the semi-random graph and meet specified spectral properties. Additionally, we propose a first-order method based on the Matrix Multiplicative Weight Update (MMWU) framework to solve the resulting SDP efficiently in nearly-linear time in the size of the semi-random comparison graph.