On the minmax regret for statistical manifolds: the role of curvature

• URL: http://arxiv.org/abs/2007.02904v1
• Date: Mon, 6 Jul 2020 17:28:19 GMT
• Title: On the minmax regret for statistical manifolds: the role of curvature
• Authors: Bruno Mera, Paulo Mateus, Alexandra M. Carvalho
• Abstract summary: Two-part codes and the minimum description length have been successful in delivering procedures to single out the best models. We derive a sharper expression than the standard one given by the complexity, where the scalar curvature of the Fisher information metric plays a dominant role.
• Score: 68.8204255655161
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model complexity plays an essential role in its selection, namely, by choosing a model that fits the data and is also succinct. Two-part codes and the minimum description length have been successful in delivering procedures to single out the best models, avoiding overfitting. In this work, we pursue this approach and complement it by performing further assumptions in the parameter space. Concretely, we assume that the parameter space is a smooth manifold, and by using tools of Riemannian geometry, we derive a sharper expression than the standard one given by the stochastic complexity, where the scalar curvature of the Fisher information metric plays a dominant role. Furthermore, we derive the minmax regret for general statistical manifolds and apply our results to derive optimal dimensional reduction in the context of principal component analysis.

Related papers

• Data-freeWeight Compress and Denoise for Large Language Models [101.53420111286952]
  We propose a novel approach termed Data-free Joint Rank-k Approximation for compressing the parameter matrices. We achieve a model pruning of 80% parameters while retaining 93.43% of the original performance without any calibration data.
  arXiv  Detail & Related papers  (2024-02-26T05:51:47Z)
• On the Consistency of Maximum Likelihood Estimation of Probabilistic Principal Component Analysis [1.0528389538549636]
  PPCA has a broad spectrum of applications ranging from science and engineering to quantitative finance. Despite this wide applicability in various fields, hardly any theoretical guarantees exist to justify the soundness of the maximal likelihood (ML) solution for this model. We propose a novel approach using quotient topological spaces and in particular, we show that the maximum likelihood solution is consistent in an appropriate quotient Euclidean space.
  arXiv  Detail & Related papers  (2023-11-08T22:40:45Z)
• Curvature-Independent Last-Iterate Convergence for Games on Riemannian Manifolds [77.4346324549323]
  We show that a step size agnostic to the curvature of the manifold achieves a curvature-independent and linear last-iterate convergence rate. To the best of our knowledge, the possibility of curvature-independent rates and/or last-iterate convergence has not been considered before.
  arXiv  Detail & Related papers  (2023-06-29T01:20:44Z)
• Riemannian Metric Learning via Optimal Transport [34.557360177483595]
  We introduce an optimal transport-based model for learning a metric from cross-sectional samples of evolving probability measures. We show that metrics learned using our method improve the quality of trajectory inference on scRNA and bird migration data.
  arXiv  Detail & Related papers  (2022-05-18T23:32:20Z)
• Statistical Analysis of Wasserstein Distributionally Robust Estimators [9.208007322096535]
  We consider statistical methods which invoke a min-max distributionally robust formulation to extract good out-of-sample performance in data-driven optimization and learning problems. The resulting Distributionally Robust Optimization (DRO) formulations are specified using optimal transportation phenomena. This tutorial is devoted to insights into the nature of the adversarials selected by the min-max formulations and additional applications of optimal transport projections.
  arXiv  Detail & Related papers  (2021-08-04T15:45:47Z)
• Bayesian Quadrature on Riemannian Data Manifolds [79.71142807798284]
  A principled way to model nonlinear geometric structure inherent in data is provided. However, these operations are typically computationally demanding. In particular, we focus on Bayesian quadrature (BQ) to numerically compute integrals over normal laws. We show that by leveraging both prior knowledge and an active exploration scheme, BQ significantly reduces the number of required evaluations.
  arXiv  Detail & Related papers  (2021-02-12T17:38:04Z)
• Understanding Implicit Regularization in Over-Parameterized Single Index Model [55.41685740015095]
  We design regularization-free algorithms for the high-dimensional single index model. We provide theoretical guarantees for the induced implicit regularization phenomenon.
  arXiv  Detail & Related papers  (2020-07-16T13:27:47Z)
• On Projection Robust Optimal Transport: Sample Complexity and Model Misspecification [101.0377583883137]
  Projection robust (PR) OT seeks to maximize the OT cost between two measures by choosing a $k$-dimensional subspace onto which they can be projected. Our first contribution is to establish several fundamental statistical properties of PR Wasserstein distances. Next, we propose the integral PR Wasserstein (IPRW) distance as an alternative to the PRW distance, by averaging rather than optimizing on subspaces.
  arXiv  Detail & Related papers  (2020-06-22T14:35:33Z)
• Fundamental Limits of Ridge-Regularized Empirical Risk Minimization in High Dimensions [41.7567932118769]
  Empirical Risk Minimization algorithms are widely used in a variety of estimation and prediction tasks. In this paper, we characterize for the first time the fundamental limits on the statistical accuracy of convex ERM for inference.
  arXiv  Detail & Related papers  (2020-06-16T04:27:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.