Marten Dijk

2 papers · 2018–2020 · 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 🐣 Hot Topic Early Bird

Venues

AISTATS (1) ICML (1)

Top co-authors

Lam Nguyen (2) PHUONG HA NGUYEN (2) Peter Richtarik (1) Martin Takac (1) Nhan Pham (1) Dzung Phan (1) Quoc Tran-Dinh (1) Katya Scheinberg (1)

Research topics

Machine Learning (2) Optimization & Theory · Machine Learning (2) Deep Learning (1) Mathematics & Optimization (1) Reinforcement Learning (1) Methods (1) Optimization (1) Optimization & Theory · Deep Learning (1)

Keywords

stochastic optimization (1) reinforcement learning (1) stochastic gradient descent (1) policy gradient (1) convergence analysis (1) composite optimization (1) empirical risk minimization (1) variance reduction (1) strongly convex (1) parallel optimization (1) learning rate (1) proximal policy optimization (1) asynchronous parallel (1) hogwild algorithm (1)

Papers

A Hybrid Stochastic Policy Gradient Algorithm for Reinforcement Learning AISTATS 2020 SGD and Hogwild! Convergence Without the Bounded Gradients Assumption ICML 2018