Kento Nozawa

4 papers · 2020–2022 · 4 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 🐣 Hot Topic Early Bird

Venues

ICML (1) IJCAI (1) NeurIPS (1) UAI (1)

Top co-authors

Issei Sato (2) Yoshihiro Nagano (1) Han Bao (1) Benjamin Guedj (1) Pascal Germain (1)

Research topics

Machine Learning (4) Core Methods (3) Learning Types · Machine Learning (3) Optimization & Theory (3) Deep Learning (1) Learning Types · Deep Learning (1)

Keywords

representation learning (3) contrastive learning (1) theoretical analysis (1) feature representation (1) generalization bound (1) downstream task (1) contrastive loss (1) pac-bayesian theory (1) instance discrimination (1) negative sample (1) contrastive representation learning (1) negative sampling (1) contrastive unsupervised representation learning (1) generalisation bound (1) downstream classification (1) supervised loss (1) surrogate bound (1) evaluation method (1) unsupervised learning (1) machine learning task (1)

Papers

Evaluation Methods for Representation Learning: A Survey IJCAI 2022 On the Surrogate Gap between Contrastive and Supervised Losses ICML 2022 Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning NeurIPS 2021 PAC-Bayesian Contrastive Unsupervised Representation Learning UAI 2020