JMLR 2024 papers on Optimization
57 of the 391 papers published in JMLR 2024 (14.6%) are on Optimization, compared with 13.3% at JMLR 2023. They fall into 4 topics.
See JMLR 2024 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 · 33 papers
- Adam-family Methods for Nonsmooth Optimization with Convergence Guarantees (21 citations)
- Optimal Algorithms for Stochastic Bilevel Optimization under Relaxed Smoothness Conditions (20 citations)
- Entropic Gromov-Wasserstein Distances: Stability and Algorithms (17 citations)
- Gradient-free optimization of highly smooth functions: improved analysis and a new algorithm (16 citations)
- Infeasible Deterministic, Stochastic, and Variance-Reduction Algorithms for Optimization under Orthogonality Constraints (10 citations)
- Stochastic Approximation with Decision-Dependent Distributions: Asymptotic Normality and Optimality (7 citations)
- An Algorithm with Optimal Dimension-Dependence for Zero-Order Nonsmooth Nonconvex Stochastic Optimization (6 citations)
- Near-Optimal Algorithms for Making the Gradient Small in Stochastic Minimax Optimization (6 citations)
- Stochastic Regularized Majorization-Minimization with weakly convex and multi-convex surrogates (6 citations)
- Optimal Scaling for the Proximal Langevin Algorithm in High Dimensions (4 citations)
- Penalized Overdamped and Underdamped Langevin Monte Carlo Algorithms for Constrained Sampling (4 citations)
- Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions (4 citations)
and 21 more in the interactive map.
Implicit bias and generalization · 16 papers
- Grokking phase transitions in learning local rules with gradient descent (16 citations)
- Generalization and Stability of Interpolating Neural Networks with Minimal Width (12 citations)
- Iterate Averaging in the Quest for Best Test Error (11 citations)
- Stochastic Modified Flows, Mean-Field Limits and Dynamics of Stochastic Gradient Descent (9 citations)
- A PDE-based Explanation of Extreme Numerical Sensitivities and Edge of Stability in Training Neural Networks (6 citations)
- Law of Large Numbers and Central Limit Theorem for Wide Two-layer Neural Networks: The Mini-Batch and Noisy Case (6 citations)
- Random Smoothing Regularization in Kernel Gradient Descent Learning (6 citations)
- Learning Discretized Neural Networks under Ricci Flow (5 citations)
- Sharpness-Aware Minimization and the Edge of Stability (4 citations)
- Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK (3 citations)
- A Comparison of Continuous-Time Approximations to Stochastic Gradient Descent
- Dropout Regularization Versus l2-Penalization in the Linear Model
and 4 more in the interactive map.
Optimizers · 7 papers
- Targeted Separation and Convergence with Kernel Discrepancies (12 citations)
- Learning to Warm-Start Fixed-Point Optimization Algorithms (11 citations)
- GGD: Grafting Gradient Descent
- Nonasymptotic analysis of Stochastic Gradient Hamiltonian Monte Carlo under local conditions for nonconvex optimization
- On the Hyperparameters in Stochastic Gradient Descent with Momentum
- Polygonal Unadjusted Langevin Algorithms: Creating stable and efficient adaptive algorithms for neural networks
- Win: Weight-Decay-Integrated Nesterov Acceleration for Faster Network Training
