Tim Erven

2 papers · 2011–2018 · 1 conference · across top CS/AI conferences

Achievements

🏃 Academic Marathon (7) 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (13) 🚀 Conference Pioneer

Conferences

COLT (2)

Top co-authors

Wojciech Kotłowski (1) Mark D. Reid (1) Robert C. Williamson (1) Dirk Hoeven (1)

Keywords

online learning (1) multiclass classification (1) mirror descent (1) log loss (1) surrogate loss (1) regret bound (1) exponential weight (1) proper loss (1) online gradient descent (1) bayes risk (1) multiclass loss (1)

Papers

The Many Faces of Exponential Weights in Online Learning COLT 2018

Mixability is Bayes Risk Curvature Relative to Log Loss COLT 2011