JMLR 2023 papers on Optimization
47 of the 354 papers published in JMLR 2023 (13.3%) are on Optimization, compared with 14.5% at JMLR 2022. They fall into 4 topics.
See JMLR 2023 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 · 26 papers
- Lower Bounds and Accelerated Algorithms for Bilevel Optimization (37 citations)
- Multiplayer Performative Prediction: Learning in Decision-Dependent Games (23 citations)
- Policy Gradient Methods Find the Nash Equilibrium in N-player General-sum Linear-quadratic Games (16 citations)
- First-Order Algorithms for Nonlinear Generalized Nash Equilibrium Problems (14 citations)
- Asynchronous Iterations in Optimization: New Sequence Results and Sharper Algorithmic Guarantees (13 citations)
- Stochastic Optimization under Distributional Drift (10 citations)
- On the Convergence of Stochastic Gradient Descent with Bandwidth-based Step Size (8 citations)
- Entropic Fictitious Play for Mean Field Optimization Problem (5 citations)
- Beyond the Golden Ratio for Variational Inequality Algorithms (4 citations)
- Limits of Dense Simplicial Complexes (2 citations)
- A Parameter-Free Conditional Gradient Method for Composite Minimization under Hölder Condition (1 citation)
- Discrete Variational Calculus for Accelerated Optimization
and 14 more in the interactive map.
Implicit bias and generalization · 13 papers
- Random Feature Amplification: Feature Learning and Generalization in Neural Networks (24 citations)
- The Dynamics of Sharpness-Aware Minimization: Bouncing Across Ravines and Drifting Towards Wide Minima (21 citations)
- Benign Overfitting of Constant-Stepsize SGD for Linear Regression (20 citations)
- Integrating Random Effects in Deep Neural Networks (15 citations)
- Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels (9 citations)
- Incremental Learning in Diagonal Linear Networks (9 citations)
- Sparse GCA and Thresholded Gradient Descent (7 citations)
- Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping (5 citations)
- A Unified Approach to Controlling Implicit Regularization via Mirror Descent (3 citations)
- On the Dynamics Under the Unhinged Loss and Beyond
- Elastic Gradient Descent, an Iterative Optimization Method Approximating the Solution Paths of the Elastic Net
- Implicit Bias of Gradient Descent for Mean Squared Error Regression with Two-Layer Wide Neural Networks
and 1 more in the interactive map.
