Stochastic Difference-of-Convex Optimization with Momentum
cs.LG, math.OC, stat.ML
Submitted: 2025-10-20
Updated: 2026-10-09
Sources
- Non-convex Stochastic Composite Optimization with Polyak Momentum
- Single-Loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions
- Three Factors Influencing Minima in SGD
- Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks