AAAI 2023 accepted papers on Optimization
28 of the 2,023 papers accepted at AAAI 2023 (1.4%) are on Optimization, compared with 2.2% at AAAI 2022. They fall into 4 topics.
See AAAI 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Optimizers · 11 papers
- FedMDFG: Federated Learning with Multi-Gradient Descent and Fair Guidance (27 citations)
- Safeguarded Learned Convex Optimization (7 citations)
- Implicit Bilevel Optimization: Differentiating through Bilevel Optimization Programming (5 citations)
- Denoising Multi-Similarity Formulation: A Self-Paced Curriculum-Driven Approach for Robust Metric Learning (3 citations)
- Efficient Gradient Approximation Method for Constrained Bilevel Optimization (3 citations)
- Learning Fractals by Gradient Descent (3 citations)
- Fast Offline Policy Optimization for Large Scale Recommendation (2 citations)
- Structured BFGS Method for Optimal Doubly Stochastic Matrix Approximation (2 citations)
- Enhance Robustness of Machine Learning with Improved Efficiency (1 citation)
- Opposite Online Learning via Sequentially Integrated Stochastic Gradient Descent Estimators (1 citation)
- Mean Estimation of Truncated Mixtures of Two Gaussians: A Gradient Based Approach
Implicit bias and generalization · 7 papers
- Implicit Stochastic Gradient Descent for Training Physics-Informed Neural Networks (6 citations)
- Stop-Gradient Softmax Loss for Deep Metric Learning (6 citations)
- The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models (6 citations)
- Fast Convergence in Learning Two-Layer Neural Networks with Separable Data (2 citations)
- Learning Compact Features via In-Training Representation Alignment (2 citations)
- On the Stability and Generalization of Triplet Learning (2 citations)
- Stability-Based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning (1 citation)
Nonconvex and smooth optimization · 6 papers
- Proximal Stochastic Recursive Momentum Methods for Nonconvex Composite Decentralized Optimization (10 citations)
- Policy-Based Primal-Dual Methods for Convex Constrained Markov Decision Processes (7 citations)
- Decentralized Riemannian Algorithm for Nonconvex Minimax Problems (4 citations)
- Coordinate Descent Methods for DC Minimization: Optimality Conditions and Global Convergence (2 citations)
- Fast and Interpretable Dynamics for Fisher Markets via Block-Coordinate Updates (1 citation)
- Linear Regularizers Enforce the Strict Saddle Property (1 citation)
Distributed and compressed · 4 papers
- Stability-Based Generalization Analysis of the Asynchronous Decentralized SGD (13 citations)
- Distributed Spectrum-Based Fault Localization (3 citations)
- Distributed Stochastic Nested Optimization for Emerging Machine Learning Models: Algorithm and Theory
- Non-reversible Parallel Tempering for Deep Posterior Approximation