Charles Guille-Escuret

5 papers · 2021–2024 · 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 (11)

Venues

NeurIPS (3) AISTATS (1) ICML (1)

Top co-authors

Ioannis Mitliagkas (5) Baptiste Goujaud (2) Joao Monteiro (2) David Vázquez (2) Pau Rodriguez (1) Manuela Girotti (1) Hiroki Naganuma (1) Adam Ibrahim (1) Pierre-André Noël (1) Kilian Fatras (1)

Research topics

Machine Learning (5) Optimization & Theory · Machine Learning (3) Deep Learning (2) Mathematics & Optimization (2) Learning Types (2) Optimization (2) Optimization & Theory · Deep Learning (2) Application Areas (1) Core Methods (1)

Keywords

anomaly detection (2) error bound (2) first-order optimization (2) restricted secant inequality (2) gradient descent (2) out-of-distribution detection (2) linear convergence (1) condition number (1) gaussian mixture model (1) convergence rate (1) learning rate schedule (1) optimization trajectories (1) contrastive learning (1) gamma ratio (1) adversarial robustness (1) domain generalization (1) self-supervised learning (1) distribution shift (1) strong convexity (1)

Papers

Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection NeurIPS 2024 No Wrong Turns: The Simple Geometry Of Neural Networks Optimization Paths ICML 2024 CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning NeurIPS 2023 Gradient Descent Is Optimal Under Lower Restricted Secant Inequality And Upper Error Bound NeurIPS 2022 A Study of Condition Numbers for First-Order Optimization AISTATS 2021