JMLR 2022 papers on Optimization
41 of the 283 papers published in JMLR 2022 (14.5%) are on Optimization, compared with 15.1% at JMLR 2021. They fall into 4 topics.
See JMLR 2022 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 · 23 papers
- Implicit Differentiation for Fast Hyperparameter Selection in Non-Smooth Convex Learning (17 citations)
- On Constraints in First-Order Optimization: A View from Non-Smooth Dynamical Systems (13 citations)
- Riemannian Stochastic Proximal Gradient Methods for Nonsmooth Optimization over the Stiefel Manifold (12 citations)
- Explicit Convergence Rates of Greedy and Random Quasi-Newton Methods (9 citations)
- Extensions to the Proximal Distance Method of Constrained Optimization (8 citations)
- Handling Hard Affine SDP Shape Constraints in RKHSs (8 citations)
- On quantitative Laplace-type convergence results for some exponential probability measures, with two applications (5 citations)
- SGD with Coordinate Sampling: Theory and Practice (3 citations)
- Stochastic DCA with Variance Reduction and Applications in Machine Learning (2 citations)
- On Acceleration for Convex Composite Minimization with Noise-Corrupted Gradients and Approximate Proximal Mapping
- Three rates of convergence or separation via U-statistics in a dependent framework
- A Stochastic Bundle Method for Interpolation
and 11 more in the interactive map.
Implicit bias and generalization · 10 papers
- Theoretical Foundations of t-SNE for Visualizing High-Dimensional Clustered Data (153 citations)
- Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training (42 citations)
- A proof of convergence for the gradient descent optimization method with random initializations in the training of neural networks with ReLU activation for piecewise linear target functions (11 citations)
- Overparameterization of Deep ResNet: Zero Loss and Mean-field Analysis (11 citations)
- Multivariate Boosted Trees and Applications to Forecasting and Control (10 citations)
- Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks (5 citations)
- Training Two-Layer ReLU Networks with Gradient Descent is Inconsistent (4 citations)
- Batch Normalization Preconditioning for Neural Network Training
- Early Stopping for Iterative Regularization with General Loss Functions
- Gaussian Process Parameter Estimation Using Mini-batch Stochastic Gradient Descent: Convergence Guarantees and Empirical Benefits
Optimizers · 5 papers
- Theoretical Convergence of Multi-Step Model-Agnostic Meta-Learning (67 citations)
- Towards Practical Adam: Non-Convexity, Convergence Theory, and Mini-Batch Acceleration (19 citations)
- A Momentumized, Adaptive, Dual Averaged Gradient Method
- Analytically Tractable Hidden-States Inference in Bayesian Neural Networks
- Boulevard: Regularized Stochastic Gradient Boosted Trees and Their Limiting Distribution
Distributed and compressed · 3 papers
- Variance Reduced EXTRA and DIGing and Their Optimal Acceleration for Strongly Convex Decentralized Optimization (36 citations)
- Asymptotic Network Independence and Step-Size for a Distributed Subgradient Method (1 citation)
- Robust Distributed Accelerated Stochastic Gradient Methods for Multi-Agent Networks
