AAAI 2022 accepted papers on Optimization
29 of the 1,319 papers accepted at AAAI 2022 (2.2%) are on Optimization, compared with 2.5% at AAAI 2021. They fall into 4 topics.
See AAAI 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 · 13 papers
- Policy Optimization with Stochastic Mirror Descent (19 citations)
- Breaking the Convergence Barrier: Optimization via Fixed-Time Convergent Flows (13 citations)
- Efficient Optimal Transport Algorithm by Accelerated Gradient Descent (12 citations)
- Decision-Dependent Risk Minimization in Geometrically Decaying Dynamic Environments (6 citations)
- Sample Average Approximation for Stochastic Optimization with Dependent Data: Performance Guarantees and Tractability (6 citations)
- Adaptive and Universal Algorithms for Variational Inequalities with Optimal Convergence (5 citations)
- Balanced Self-Paced Learning for AUC Maximization (5 citations)
- Gradient Temporal Difference with Momentum: Stability and Convergence (4 citations)
- Convergence and Optimality of Policy Gradient Methods in Weakly Smooth Settings (3 citations)
- Efficient Decentralized Stochastic Gradient Descent Method for Nonconvex Finite-Sum Optimization Problems (2 citations)
- HNO: High-Order Numerical Architecture for ODE-Inspired Deep Unfolding Networks (2 citations)
- Anytime Guarantees under Heavy-Tailed Data (1 citation)
and 1 more in the interactive map.
Optimizers · 12 papers
- Fast and Robust Online Inference with Stochastic Gradient Descent via Random Scaling (19 citations)
- A Fully Single Loop Algorithm for Bilevel Optimization without Hessian Inverse (16 citations)
- Coordinating Followers to Reach Better Equilibria: End-to-End Gradient Descent for Stackelberg Games (13 citations)
- Coordinate Descent on the Orthogonal Group for Recurrent Neural Network Training (7 citations)
- Toward Physically Realizable Quantum Neural Networks (7 citations)
- Efficient Riemannian Meta-Optimization by Implicit Differentiation (5 citations)
- Better Parameter-Free Stochastic Optimization with ODE Updates for Coin-Betting (3 citations)
- DPCD: Discrete Principal Coordinate Descent for Binary Variable Problems (3 citations)
- Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs (3 citations)
- Learning Large DAGs by Combining Continuous Optimization and Feedback Arc Set Heuristics (3 citations)
- Exploiting Invariance in Training Deep Neural Networks (2 citations)
- KOALA: A Kalman Optimization Algorithm with Loss Adaptivity (2 citations)
