Phillip Gibbons

3 papers · 2018–2023 · 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 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird

Venues

ICML (2) NeurIPS (1)

Top co-authors

Ellango Jothimurugesan (1) Pratik Pramod Fegade (1) Todd Mowry (1) Kevin Hsieh (1) Ashraf Tahmasbi (1) Onur Mutlu (1) Siyuan Chen (1) Tianqi Chen (1) Srikanta Tirthapura (1) Amar Phanishayee (1)

Research topics

Machine Learning (3) Application Areas (2) Optimization & Theory · Machine Learning (2) Deep Learning (1) Mathematics & Optimization (1) Learning Types (1) Optimization (1) Optimization & Theory · Deep Learning (1)

Keywords

reinforcement learning (1) stochastic gradient descent (1) online learning (1) batch normalization (1) variance reduction (1) streaming data (1) competitive analysis (1) non-iid data (1) dynamic neural network (1) decentralized learning (1) finite state machine (1) automatic batching (1) memory planning (1) group normalization (1) data distribution skew (1)

Papers

ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines ICML 2023 The Non-IID Data Quagmire of Decentralized Machine Learning ICML 2020 Variance-Reduced Stochastic Gradient Descent on Streaming Data NeurIPS 2018