Majorizing Measures for the Optimizer

  title={Majorizing Measures for the Optimizer},
  author={Sander Borst and Daniel Dadush and Neil Olver and Makrand Sinha},
The theory of majorizing measures, extensively developed by Fernique, Talagrand and many others, provides one of the most general frameworks for controlling the behavior of stochastic processes. In particular, it can be applied to derive quantitative bounds on the expected suprema and the degree of continuity of sample paths for many processes. One of the crowning achievements of the theory is Talagrand’s tight alternative characterization of the suprema of Gaussian processes in terms of… Expand
Generalization Properties of Stochastic Optimizers via Trajectory Analysis
An encompassing theoretical framework for investigating the generalization properties of stochastic optimizers, which is based on their dynamics, and it is shown that both the Fernique–Talagrand functional and the local power-law exponent are predictive of generalization performance. Expand


Cover times, blanket times, and majorizing measures
A deterministic polynomial-time algorithm is given that computes the cover time to within an O(1) factor for any graph, answering a question of Aldous and Fill (1994) and positively resolving the blanket time conjectures of Winkler and Zuckerman (1996). Expand
Majorizing measures: the generic chaining
Majorizing measures provide bounds for the supremum of stochastic processes. They represent the most general possible form of the chaining argument going back to Kolmogorov. Majorizing measures aroseExpand
Supremum of a Process in Terms of Trees
In this paper we study the quantity \(\mathbb{E} \sup_{{t \in T}}X_{t},\) where X t is some random process. In the case of the Gaussian process, there is a natural sub-metric d defined on T. We findExpand
The majorizing measure approach to the sample boundedness
In this paper we describe the alternative approach to the sample boundedness and continuity of stochastic processes. We show that the regularity of paths can be understood in terms of a distributionExpand
Fast, Deterministic and Sparse Dimensionality Reduction
We provide a deterministic construction of the sparse Johnson-Lindenstrauss transform of Kane & Nelson (J.ACM 2014) which runs, under a mild restriction, in the time necessary to apply the sparseExpand
An improved cutting plane method for convex optimization, convex-concave games, and its applications
A novel multi-layered data structure for leverage score maintenance is achieved by a sophisticated combination of diverse techniques such as random projection, batched low-rank update, inverse maintenance, polynomial interpolation, and fast rectangular matrix multiplication. Expand
A theorem on majorizing measures
Let (T,d) be a metric space and φ:R + → 1R an increasing, convex function with φ(0) = 0. We prove that if m is a probability measure m on r which is majorizing with respect to d, φ, that is, &:=Expand
Sample Boundedness of Stochastic Processes Under Increment Conditions
Let (T, d) be a compact metric space of diameter D, and ∥• be an Orlicz norm. When is it true that all (separable) processes (X t ) t∈T that satisfy the increment condition ∥X t −X s ∥≤d(t, s) forExpand
The Sizes of Compact Subsets of Hilbert Space and Continuity of Gaussian Processes
The first two sections of this paper are introductory and correspond to the two halves of the title. As is well known, there is no complete analog of Lebesue or Haar measure in anExpand
A polynomial time approximation scheme for computing the supremum of Gaussian processes
A polynomial time approximation scheme (PTAS) for computing the supremum of a Gaussian process and an explicit oblivious estimator for semi-norms in Gaussian space with optimal query complexity is given. Expand