JMLR 2018 papers on Optimization
21 of the 164 papers published in JMLR 2018 (12.8%) are on Optimization, compared with 12.9% at JMLR 2017. They fall into 4 topics.
See JMLR 2018 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Nonconvex and smooth optimization · 16 papers
- Katyusha: The First Direct Acceleration of Stochastic Gradient Methods (309 citations)
- CoCoA: A General Framework for Communication-Efficient Distributed Optimization (222 citations)
- Gradient Descent Learns Linear Dynamical Systems (179 citations)
- Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice (111 citations)
- Maximum Principle Based Algorithms for Deep Learning (105 citations)
- Nonasymptotic convergence of stochastic proximal point methods for constrained convex optimization (58 citations)
- Improved Asynchronous Parallel Optimization Analysis for Stochastic Incremental Methods (48 citations)
- Average Stability is Invariant to Data Preconditioning. Implications to Exp-concave Empirical Risk Minimization (26 citations)
- Local Rademacher Complexity-based Learning Guarantees for Multi-Task Learning (17 citations)
- Saturating Splines and Feature Selection (17 citations)
- Convergence of Unregularized Online Learning Algorithms (12 citations)
- On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization (7 citations)
and 4 more in the interactive map.
