Baptiste Goujaud

5 papers · 2019–2024 · 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 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird

Venues

AISTATS (3) NeurIPS (2)

Top co-authors

Aymeric Dieuleveut (2) Charles Guille-Escuret (2) Ioannis Mitliagkas (2) Damien Ferbach (1) Manuela Girotti (1) Gauthier Gidel (1) Rahaf Aljundi (1) Min Lin (1) Yoshua Bengio (1) Adrien B. Taylor (1)

Research topics

Machine Learning (5) Optimization & Theory · Machine Learning (5) Mathematics & Optimization (4) Optimization (4) Deep Learning (3) Optimization & Theory · Deep Learning (3) Learning Types (1) Mathematics (1)

Keywords

gradient descent (3) first-order optimization (2) convergence rate (2) stochastic gradient descent (1) logistic regression (1) optimal transport (1) loss landscape (1) constrained optimization (1) energy landscape (1) strong convexity (1) condition number (1) sample selection (1) first-order method (1) replay buffer (1) momentum method (1) linear mode connectivity (1) mode connectivity (1) error bound (1) cyclical learning rate (1) quadratic minimization (1)

Papers

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport AISTATS 2024 Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound NeurIPS 2022 Super-Acceleration with Cyclical Step-sizes AISTATS 2022 A Study of Condition Numbers for First-Order Optimization AISTATS 2021 Gradient based sample selection for online continual learning NeurIPS 2019