Orthogonal Updates for the Win: Towards Accelerated Adaptive Minimax Optimization
cs.LG, math.OC, stat.ML
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/Zeleni9/pytorch-wgan
Terminology
Sources
- ASGO: Adaptive Structured Gradient Optimization
- Old Optimizer, New Norm: An Anthology
- Training GANs with Optimism
- Low-rank Orthogonalization for Large-scale Matrix Optimization with Applications to Foundation Model Training
- Provable Complexity Improvement of AdaGrad over SGD: Upper and Lower Bounds in Stochastic Non-Convex Optimization
- What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization?
- Adam: A Method for Stochastic Optimization
- PolarGrad: A Class of Matrix-Gradient Optimizers from a Unifying Preconditioning Perspective
- TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
- Muon is Scalable for LLM Training
- COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs
- Decoupled Weight Decay Regularization
- Adaptive Gradient Methods with Dynamic Bound of Learning Rate
- Adaptive Gradient Descent without Descent
- Adaptive Bound Optimization for Online Convex Optimization
- On the Convergence Analysis of Muon
- AdaMuon: Adaptive Muon Optimizer
- Certifying Some Distributional Robustness with Principled Adversarial Training
- Wasserstein GANs are Minimax Optimal Distribution Estimators
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis