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/

Zendy Plus

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

Zendy Tools

Zendy Open

In this paper, our aim is to analyse the generalization capabilities offirst-order methods for statistical learning in multiple, different yetrelated, scenarios including supervised learning, transfer learning, robustlearning and federated learning. To do so, we provide sharp upper and lowerbounds for the minimax excess risk of strongly convex and smooth statisticallearning when the gradient is accessed through partial observations given by adata-dependent oracle. This novel class of oracles can query the gradient withany given data distribution, and is thus well suited to scenarios in which thetraining data distribution does not match the target (or test) distribution. Inparticular, our upper and lower bounds are proportional to the smallest meansquare error achievable by gradient estimators, thus allowing us to easilyderive multiple sharp bounds in the aforementioned scenarios using theextensive literature on parameter estimation.

Minimax Excess Risk of First-Order Methods for Statistical Learning with Data-Dependent Oracles