Adrien Taylor

10 papers · 2018–2025 · 5 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 ↓

+3 more ↓

🗺️ Taxonomy Completionist (12) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Bronze 🧬 Topic Evolution

🗃️ Keyword Collector (53) 🔥 Unstoppable · Bronze 💎 Century Club · Bronze

Venues

ICML (3) NeurIPS (3) COLT (2) ICLR (1) RSS (1)

Top co-authors

Francis Bach (2) Eduard Gorbunov (2) Gauthier Gidel (2) Antoine Bambade (2) Francis R. Bach (2) Justin Carpentier (2) Fabian Schaipp (1) Benjamin Dubois-Taine (1) Alexander Hägele (1) Mathieu Barré (1)

Research topics

Machine Learning (8) Optimization & Theory · Machine Learning (8) Mathematics & Optimization (7) Optimization (7) Deep Learning (2) Reinforcement Learning (1) Applications (1) Mathematics (1) Models (1) Optimization & Theory · Deep Learning (1)

Keywords

convex optimization (3) first-order method (2) convergence rate (2) convergence analysis (2) variational inequality (2) augmented lagrangian (2) quadratic programming (2) differentiable programming (1) robotics control (1) stochastic gradient descent (1) gradient descent (1) asynchronous computation (1) linear convergence (1) strong convexity (1) lyapunov function (1) strongly convex optimization (1) accelerated gradient (1) parallel computing (1) block coordinate descent (1) numerical optimization (1)

Papers

The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training ICML 2025 Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning ICLR 2024 Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity ICML 2023 Fast Stochastic Composite Minimization and an Accelerated Frank-Wolfe Algorithm under Parallelization NeurIPS 2022 Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities NeurIPS 2022 PROX-QP: Yet another Quadratic Programming Solver for Robotics and beyond RSS 2022 Continuized Accelerations of Deterministic and Stochastic Gradient Descents, and of Gossip Algorithms NeurIPS 2021 Complexity Guarantees for Polyak Steps with Momentum COLT 2020 Stochastic first-order methods: non-asymptotic and computer-aided analyses via potential functions COLT 2019 Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees ICML 2018