Mihaela Rosca

5 papers · 2018–2022 · 3 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13) 🐣 Hot Topic Early Bird

Venues

ICML (2) NeurIPS (2) JMLR (1)

Top co-authors

Shakir Mohamed (3) Benoit Dherin (1) Michael Munn (1) Cyprien de Masson d'Autume (1) David Barrett (1) Oriol Vinyals (1) Jack Rae (1) Michael Figurnov (1) Yan Wu (1) Timothy Lillicrap (1)

Research topics

Machine Learning (4) Deep Learning (3) Optimization & Theory · Machine Learning (3) Artificial Intelligence (2) Models (2) Mathematics & Optimization (1) Core AI (1) Core Methods (1) Learning Paradigms (1) Learning Types (1) Optimization (1) Optimization & Theory · Deep Learning (1)

Keywords

generative adversarial network (2) natural language generation (1) text generation (1) adversarial training (1) maximum likelihood (1) variance reduction (1) sensitivity analysis (1) signal recovery (1) implicit regularization (1) language model (1) geometric complexity (1) language generation (1) parameter initialization (1) frechet inception distance (1) mode collapse (1) implicit generative model (1) dirichlet energy (1) method of moment (1) score function estimator (1) path-wise gradient estimator (1)

Papers

Why neural networks find simple solutions: The many regularizers of geometric complexity NeurIPS 2022 Monte Carlo Gradient Estimation in Machine Learning JMLR 2020 Deep Compressed Sensing ICML 2019 Training Language GANs from Scratch NeurIPS 2019 Learning Implicit Generative Models with the Method of Learned Moments ICML 2018