English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We consider an online two-stage stochastic optimization with long-termconstraints over a finite horizon of $T$ periods. At each period, we take thefirst-stage action, observe a model parameter realization and then take thesecond-stage action from a feasible set that depends both on the first-stagedecision and the model parameter. We aim to minimize the cumulative objectivevalue while guaranteeing that the long-term average second-stage decisionbelongs to a set. We develop online algorithms for the online two-stage problemfrom adversarial learning algorithms. Also, the regret bound of our algorithmcan be reduced to the regret bound of embedded adversarial learning algorithms.Based on this framework, we obtain new results under various settings. When themodel parameters are drawn from unknown non-stationary distributions and we aregiven machine-learned predictions of the distributions, we develop a newalgorithm from our framework with a regret $O(W_T+\sqrt{T})$, where $W_T$measures the total inaccuracy of the machine-learned predictions. We thendevelop another algorithm that works when no machine-learned predictions aregiven and show the performances.

Constrained Online Two-stage Stochastic Optimization: Algorithm with (and without) Predictions