conftrace_

Raphael Gontijo-Lopes

3 papers · 2021–2022 · 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 🐣 Hot Topic Early Bird

Venues

ICLR (2) ICML (1)

Top co-authors

Ekin Dogus Cubuk (2) Samir Ya Gadre (1) Yair Carmon (1) Yann Dauphin (1) Hongseok Namkoong (1) Gabriel Ilharco (1) Mitchell Wortsman (1) Simon Kornblith (1) Ethan Dyer (1) Ali Farhadi (1)

Research topics

Machine Learning (3) Application Areas (3) Core Methods (2) Learning Types · Machine Learning (2) Optimization & Theory (2) Deep Learning (1) Learning Types · Deep Learning (1) Techniques (1)

Keywords

model ensemble (2) contrastive learning (1) feature learning (1) domain generalization (1) transfer learning (1) domain adaptation (1) data augmentation (1) model merging (1) loss landscape (1) distribution shift (1) weight averaging (1) inference efficiency (1) out-of-distribution performance (1) zero-shot performance (1) representation learning (1) augmentation diversity (1)

Papers

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time ICML 2022 No One Representation to Rule Them All: Overlapping Features of Training Methods ICLR 2022 Tradeoffs in Data Augmentation: An Empirical Study ICLR 2021