Achraf Bahamou

3 papers · 2020–2023 · 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 🐣 Hot Topic Early Bird

Venues

AISTATS (1) ICML (1) NeurIPS (1)

Top co-authors

Donald Goldfarb (2) Yi Ren (2) Achille Nazaret (1) Valerii Likhosherstov (1) Aldo Pacchiano (1) Tamas Sarlos (1) David Cheikhi (1) Vikas Sindhwani (1) Jared Davis (1) Yuan Gao (1)

Research topics

Machine Learning (3) Optimization & Theory · Machine Learning (3) Deep Learning (2) Reinforcement Learning (1) Architectures (1) Core Methods (1) Methods (1) Optimization & Theory · Deep Learning (1)

Keywords

stochastic optimization (1) stochastic gradient (1) neural network training (1) second-order optimization (1) geometric optimization (1) quasi-newton method (1) normalizing flow (1) model training (1) lie group (1) second-order method (1) fisher matrix (1) orthogonal group (1) block-diagonal preconditioning (1) neural network (1) kronecker factorization (1) empirical fisher (1)

Papers

A Mini-Block Fisher Method for Deep Neural Networks AISTATS 2023 Practical Quasi-Newton Methods for Training Deep Neural Networks NeurIPS 2020 Stochastic Flows and Geometric Optimization on the Orthogonal Group ICML 2020