AAAI 2024 accepted papers on Optimization
33 of the 2,864 papers accepted at AAAI 2024 (1.2%) are on Optimization, compared with 1.4% at AAAI 2023. They fall into 4 topics.
See AAAI 2024 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
Nonconvex and smooth optimization · 12 papers
- PPO-Clip Attains Global Optimality: Towards Deeper Understandings of Clipping (22 citations)
- Provably Convergent Federated Trilevel Learning (6 citations)
- On Partial Optimal Transport: Revising the Infeasibility of Sinkhorn and Efficient Gradient Methods (5 citations)
- Trust Region Methods for Nonconvex Stochastic Optimization beyond Lipschitz Smoothness (4 citations)
- Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization (3 citations)
- Decentralized Gradient-Free Methods for Stochastic Non-smooth Non-convex Optimization (2 citations)
- Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization (2 citations)
- Efficient Learning in Polyhedral Games via Best-Response Oracles (1 citation)
- Large-Scale Non-convex Stochastic Constrained Distributionally Robust Optimization (1 citation)
- Decentralized Sum-of-Nonconvex Optimization
- Incremental Quasi-Newton Methods with Faster Superlinear Convergence Rates
- A Bregman Proximal Stochastic Gradient Method with Extrapolation for Nonconvex Nonsmooth Problems
Optimizers · 12 papers
- MetaDiff: Meta-Learning with Conditional Diffusion for Few-Shot Learning (68 citations)
- Runtime Analysis of the SMS-EMOA for Many-Objective Optimization (38 citations)
- EG-NAS: Neural Architecture Search with Fast Evolutionary Exploration (19 citations)
- QLABGrad: A Hyperparameter-Free and Convergence-Guaranteed Scheme for Deep Learning (10 citations)
- GradTree: Learning Axis-Aligned Decision Trees with Gradient Descent (6 citations)
- SDGMNet: Statistic-Based Dynamic Gradient Modulation for Local Descriptor Learning (6 citations)
- Exponential Hardness of Optimization from the Locality in Quantum Neural Networks (5 citations)
- One-Step Forward and Backtrack: Overcoming Zig-Zagging in Loss-Aware Quantization Training (5 citations)
- ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-Order Optimization (5 citations)
- On Estimating the Gradient of the Expected Information Gain in Bayesian Experimental Design (3 citations)
- Limited Memory Online Gradient Descent for Kernelized Pairwise Learning with Dynamic Averaging (2 citations)
- Accelerating Cutting-Plane Algorithms via Reinforcement Learning Surrogates (1 citation)
Distributed and compressed · 6 papers
- Byzantine-Robust Decentralized Learning via Remove-then-Clip Aggregation (9 citations)
- DePRL: Achieving Linear Convergence Speedup in Personalized Decentralized Learning with Shared Representations (7 citations)
- Jointly Improving the Sample and Communication Complexities in Decentralized Stochastic Minimax Optimization (5 citations)
- Towards Stability and Generalization Bounds in Decentralized Minibatch Stochastic Gradient Descent (4 citations)
- Communication Efficient Distributed Newton Method over Unreliable Networks (1 citation)
- Robust Distributed Gradient Aggregation Using Projections onto Gradient Manifolds (1 citation)