Author

Martin T. Wells

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Oct 2026

The Price of Current-Effect Inference in Nonstationary Multi-Armed Bandits

Adaptive experiments use bandit algorithms to favor interventions with higher expected rewards. However, decision-makers also require reliable inference on current treatment effects: differences between intervention and reference-arm mean rewards at the present time, rather than historical averages. These objectives co...

Sharan Sahu, Martin T. Wells · 0 citations

#machine learning May 2026

Adapt or Forget: Provable Tradeoffs Between Adam and SGD in Nonstationary Optimization

Borders reveal a noise--drift tradeoff: in noise-dominated regimes, first-moment averaging and adaptive preconditioning can yield favorable upper guarantees, whereas in drift-dominated regimes, stale first-moment information and preconditioning can enlarge Adam's tracking guarantee, potentially allowing vanilla SGD to...

Sharan Sahu, Abir Sarkar, Cameron J. Hogan et al. · arXiv.org · 0 citations