JMLR 2026 papers on Optimization
30 of the 196 papers published in JMLR 2026 (15.3%) are on Optimization, compared with 17.1% at JMLR 2025. They fall into 4 topics.
See JMLR 2026 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 · 15 papers
- Finite-Time Decoupled Convergence in Nonlinear Two-Time-Scale Stochastic Approximation (15 citations)
- Minimax Optimal Convergence of Gradient Descent in Logistic Regression via Large and Adaptive Stepsizes (12 citations)
- A Fully Parameter-Free Second-Order Algorithm for Convex-Concave Minimax Problems (4 citations)
- A Neural Network Approach to Learning Solutions of a Class of Elliptic Variational Inequalities (4 citations)
- A Provably Convergent Plug-and-Play Framework for Stochastic Bilevel Optimization (1 citation)
- A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance (1 citation)
- On the Effectiveness of the z-Transform Method in Quadratic Optimization (1 citation)
- The Sample Complexity of Parameter-Free Stochastic Convex Optimization (1 citation)
- A Single-Loop Stochastic Proximal Quasi-Newton Method for Large-Scale Nonsmooth Convex Optimization
- Near-optimal Delta-convex Estimation of Lipschitz Functions
- Convergence and complexity of block majorization-minimization for constrained block-Riemannian optimization
- Convergence of Decentralized Stochastic Subgradient-based Methods for Nonsmooth Nonconvex Optimization
and 3 more in the interactive map.
Implicit bias and generalization · 12 papers
- Optimal Convergence Rates for Neural Operators (11 citations)
- Asymptotics of Stochastic Gradient Descent with Dropout Regularization in Linear Models (8 citations)
- Singular-limit analysis of gradient descent with noise injection (8 citations)
- High-Dimensional Analysis of Gradient Flow for Extensive-Width Quadratic Neural Networks (6 citations)
- Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection (6 citations)
- Guaranteed Nonconvex Low-Rank Tensor Estimation via Scaled Gradient Descent (3 citations)
- Stochastic Differential Equations models for Least-Squares Stochastic Gradient Descent (3 citations)
- A Mean-Field Analysis of Neural Stochastic Gradient Descent-Ascent for Functional Minimax Optimization (1 citation)
- A Functional-Space Mean-Field Theory of Partially-Trained Three-Layer Neural Networks
- Cheap Bootstrap for Fast Uncertainty Quantification of Stochastic Gradient Descent
- Optimization and Generalization of Gradient Descent for Shallow ReLU Networks with Minimal Width
- Reparameterized Complex-valued Neurons Can Efficiently Learn More than Real-valued Neurons via Gradient Descent
