Non-stationary Stochastic Optimization with Local Spatial and Temporal Changes

08/09/2017
by   Xi Chen, et al.
0

We consider a non-stationary sequential stochastic optimization problem, in which the underlying cost functions change over time under a variation budget constraint. We propose an L_p,q-variation functional to quantify the change, which captures local spatial and temporal variations of the sequence of functions. Under the L_p,q-variation functional constraint, we derive both upper and matching lower regret bounds for smooth and strongly convex function sequences, which generalize previous results in (Besbes et al., 2015). Our results reveal some surprising phenomena under this general variation functional, such as the curse of dimensionality of the function domain. The key technical novelties in our analysis include an affinity lemma that characterizes the distance of the minimizers of two convex functions with bounded L_p difference, and a cubic spline based construction that attains matching lower bounds.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/20/2013

Non-stationary Stochastic Optimization

We consider a non-stationary variant of a sequential stochastic optimiza...
research
10/11/2022

On Adaptivity in Non-stationary Stochastic Optimization With Bandit Feedback

In this paper we study the non-stationary stochastic optimization questi...
research
02/09/2023

Optimistic Online Mirror Descent for Bridging Stochastic and Adversarial Online Convex Optimization

Stochastically Extended Adversarial (SEA) model is introduced by Sachs e...
research
08/29/2019

Stochastic Successive Convex Approximation for General Stochastic Optimization Problems

One key challenge for solving a general stochastic optimization problem ...
research
03/10/2023

Provably Efficient Model-Free Algorithms for Non-stationary CMDPs

We study model-free reinforcement learning (RL) algorithms in episodic n...
research
09/30/2020

Adaptive Online Estimation of Piecewise Polynomial Trends

We consider the framework of non-stationary stochastic optimization [Bes...
research
01/23/2023

A noisy-input generalised additive model for relative sea-level change along the Atlantic coast of North America

We propose a Bayesian, noisy-input, spatial-temporal generalised additiv...

Please sign up or login with your details

Forgot password? Click here to reset