Damien Ferbach

3 papers · 2023–2024 · 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 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird

Venues

AISTATS (1) ICLR (1) NeurIPS (1)

Top co-authors

Gauthier Gidel (3) Quentin Bertrand (1) Joey Bose (1) Christos Tsirigotis (1) Baptiste Goujaud (1) Avishek Joey Bose (1) Aymeric Dieuleveut (1)

Research topics

Deep Learning (3) Machine Learning (3) Optimization & Theory · Machine Learning (3) Artificial Intelligence (1) Mathematics & Optimization (1) Architectures (1) Learning Paradigms (1) Learning Types (1) Mathematics (1) Models (1) Optimization (1) Optimization & Theory · Deep Learning (1)

Keywords

wasserstein distance (1) neural network pruning (1) stochastic gradient descent (1) optimal transport (1) preference optimization (1) loss landscape (1) energy landscape (1) generative model (1) reward model (1) model collapse (1) linear mode connectivity (1) mode connectivity (1) group equivariance (1) weight permutation (1) data curation (1) random initialization (1) strong lottery ticket hypothesis (1) equivariant network (1) neural network (1) iterative retraining (1)

Papers

Proving Linear Mode Connectivity of Neural Networks via Optimal Transport AISTATS 2024 Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences NeurIPS 2024 A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis ICLR 2023