AAAI 2025 accepted papers on Optimization
41 of the 3,486 papers accepted at AAAI 2025 (1.2%) are on Optimization, compared with 1.2% at AAAI 2024. They fall into 4 topics.
See AAAI 2025 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 · 16 papers
- Locally Convex Global Loss Network for Decision-Focused Learning (6 citations)
- PSMGD: Periodic Stochastic Multi-Gradient Descent for Fast Multi-Objective Optimization (6 citations)
- Contextual Stochastic Optimization for School Desegregation Policymaking (4 citations)
- Task-Specific Preconditioner for Cross-Domain Few-Shot Learning (3 citations)
- Neural Combinatorial Optimization for Stochastic Flexible Job Shop Scheduling Problems (2 citations)
- Coupling-based Convergence Diagnostic and Stepsize Scheme for Stochastic Gradient Descent (1 citation)
- Leveraging First and Zeroth-Order Gradient to Address Imbalanced Black-Box Prompt Tuning via Minimax Optimization (1 citation)
- Memory-Reduced Meta-Learning with Guaranteed Convergence (1 citation)
- A Stochastic Approach to Bi-Level Optimization for Hyperparameter Optimization and Meta Learning
- Approximating Metric Magnitude of Point Sets
- Fast and Slow Gradient Approximation for Binary Neural Network Optimization
- HVAdam: A Full-Dimension Adaptive Optimizer
and 4 more in the interactive map.
Nonconvex and smooth optimization · 16 papers
- Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization (3 citations)
- Beyond Monotonicity: On the Convergence of Learning Algorithms in Standard Auction Games (2 citations)
- An Enhanced Levenberg--Marquardt Method via Gram Reduction (1 citation)
- Convergence Rate in a Nonlinear Two-Time-Scale Stochastic Approximation with State (Time)-Dependence (1 citation)
- Decentralized Projected Riemannian Stochastic Recursive Momentum Method for Nonconvex Optimization (1 citation)
- GPU-Accelerated Parallel Bilevel Optimization for Roubst 6G ISAC (1 citation)
- Langevin Monte Carlo Beyond Lipschitz Gradient Continuity (1 citation)
- Langevin Multiplicative Weights Update with Applications in Polynomial Portfolio Management (1 citation)
- Last-iterate Convergence in Regularized Graphon Mean Field Game (1 citation)
- Stability and Generalization of Zeroth-Order Decentralized Stochastic Gradient Descent with Changing Topology (1 citation)
- De-singularity Subgradient for the q-th-Powered lₚ-Norm Weber Location Problem
- Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates
and 4 more in the interactive map.
Implicit bias and generalization · 6 papers
- Convergence Analysis of Federated Learning Methods Using Backward Error Analysis (2 citations)
- A Method for Enhancing Generalization of Adam by Multiple Integrations (1 citation)
- From Logistic Regression to the Perceptron Algorithm: Exploring Gradient Descent with Large Step Sizes (1 citation)
- Effects of Momentum in Implicit Bias of Gradient Flow for Diagonal Linear Networks
- Error Analysis Affected by Heavy-Tailed Gradients for Non-Convex Pairwise Stochastic Gradient Descent
- Explicit and Implicit Graduated Optimization in Deep Neural Networks
Distributed and compressed · 3 papers
- AdaGK-SGD: Adaptive Global Knowledge Guided Distributed Stochastic Gradient Descent (1 citation)
- Accelerated Methods with Compressed Communications for Distributed Optimization Problems Under Data Similarity
- Hybrid Decentralized Optimization: Leveraging Both First- and Zeroth-Order Optimizers for Faster Convergence