DeepAI AI Chat
Log In Sign Up

Instability, Computational Efficiency and Statistical Accuracy

by   Nhat Ho, et al.

Many statistical estimators are defined as the fixed point of a data-dependent operator, with estimators based on minimizing a cost function being an important special case. The limiting performance of such estimators depends on the properties of the population-level operator in the idealized limit of infinitely many samples. We develop a general framework that yields bounds on statistical accuracy based on the interplay between the deterministic convergence rate of the algorithm at the population level, and its degree of (in)stability when applied to an empirical object based on n samples. Using this framework, we analyze both stable forms of gradient descent and some higher-order and unstable algorithms, including Newton's method and its cubic-regularized variant, as well as the EM algorithm. We provide applications of our general results to several concrete classes of models, including Gaussian mixture estimation, single-index models, and informative non-response models. We exhibit cases in which an unstable algorithm can achieve the same statistical accuracy as a stable algorithm in exponentially fewer steps—namely, with the number of iterations being reduced from polynomial to logarithmic in sample size n.


page 1

page 2

page 3

page 4


Towards Statistical and Computational Complexities of Polyak Step Size Gradient Descent

We study the statistical and computational complexities of the Polyak st...

Statistical guarantees for the EM algorithm: From population to sample-based analysis

We develop a general framework for proving rigorous guarantees on the pe...

Improving Computational Complexity in Statistical Models with Second-Order Information

It is known that when the statistical models are singular, i.e., the Fis...

An Exponentially Increasing Step-size for Parameter Estimation in Statistical Models

Using gradient descent (GD) with fixed or decaying step-size is standard...

One-Step Estimation With Scaled Proximal Methods

We study statistical estimators computed using iterative optimization me...

Observable adjustments in single-index models for regularized M-estimators

We consider observations (X,y) from single index models with unknown lin...