Skip to content
conftrace_

Olivier HUMBERT

2 papers · 2023–2023 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌍 Conference Polyglot · Bronze ❓ The Questioner

Venues

ICLR (1) ICML (1)

Top co-authors

Pierre-Alexandre Mattei (2) Hugo Schmutz (2) Aude Sportisse (1) Charles Bouveyron (1)

Research topics

Machine Learning (2) Learning Types · Machine Learning (2) Artificial Intelligence (1) Deep Learning (1) Learning Paradigms (1) Learning Types · Deep Learning (1) Optimization & Theory (1)

Keywords

semi-supervised learning (2) statistical learning theory (1) model calibration (1) generalization error bound (1) likelihood ratio test (1) missing data (1) inverse propensity weighting (1) missing data mechanism (1) informative label (1) label informative (1) pseudo-label method (1) debiased risk estimation (1)

Papers

Are labels informative in semi-supervised learning? Estimating and leveraging the missing-data mechanism. ICML 2023 Don’t fear the unlabelled: safe semi-supervised learning via debiasing ICLR 2023