Daouda Sow

4 papers · 2022–2025 · 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11)

Venues

ICLR (2) NeurIPS (2)

Top co-authors

Yingbin Liang (4) Kaiyi Ji (2) Sen Lin (2) Shiqiang Wang (1) Herbert Woisetschläger (1) Ness Shroff (1) Zhangyang Wang (1) Hans Arno Jacobsen (1) Saikiran Bulusu (1)

Research topics

Machine Learning (4) Optimization & Theory (4) Mathematics & Optimization (2) Learning Types (2) Optimization (2) Artificial Intelligence (1) Application Areas (1) Learning Paradigms · Artificial Intelligence (1) Learning Paradigms · Machine Learning (1)

Keywords

bilevel optimization (2) adversarial robustness (1) few-shot learning (1) online learning (1) non-convex optimization (1) kl divergence (1) adversarial training (1) online optimization (1) distributionally robust optimization (1) regret bound (1) convergence rate (1) sublinear regret (1) instance weighting (1) hypergradient estimation (1) stochastic method (1) dynamic re-weighting (1) hessian-free optimization (1) response jacobian (1) instance-level reweighting (1) gradient convergence (1)

Papers

Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining ICLR 2025 Doubly Robust Instance-Reweighted Adversarial Training ICLR 2024 Non-Convex Bilevel Optimization with Time-Varying Objective Functions NeurIPS 2023 On the Convergence Theory for Hessian-Free Bilevel Algorithms NeurIPS 2022