Andrea Agazzi

3 papers · 2021–2025 · 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 🌉 Interdisciplinary Bridge · Bronze 📈 Trend Setter

Venues

ICLR (2) ICML (1)

Top co-authors

Jianfeng Lu (2) Giuseppe Bruno (1) Federico Pasqualotto (1) Sayan Mukherjee (1)

Research topics

Deep Learning (2) Machine Learning (2) Architectures (2) Optimization & Theory · Machine Learning (2) Optimization & Theory · Deep Learning (2) Mathematics & Optimization (1) Learning Types (1) Mathematics (1)

Keywords

global optimality (2) mean-field regime (2) policy gradient (1) gradient descent (1) mean-field approximation (1) recurrent neural network (1) entropy regularization (1) partial differential equation (1) gradient flow (1) infinite-width limit (1) transformer model (1) softmax policy (1) elman recurrent neural network (1) meta-stable state (1) reinforcement learning (1) clustering phenomenon (1) feature learning (1)

Papers

Emergence of meta-stable clustering in mean-field transformer models ICLR 2025 Global optimality of Elman-type RNNs in the mean-field regime ICML 2023 Global optimality of softmax policy gradient with single hidden layer neural networks in the mean-field regime ICLR 2021