The Optimal Rate Constant of Heavy-Ball Momentum on Smooth Strongly Convex Functions
cs.LG, math.OC
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/marcoshernanz/heavy-ball-optimal-rate
Terminology
Sources
- An Extension Theorem for convex functions of class $C^{1,1}$ on Hilbert spaces
- Entropic Risk-Averse Generalized Momentum Methods
- Non-monotone Behavior of the Heavy Ball Method
- On the oracle complexity of smooth strongly convex minimization
- Performance of first-order methods for smooth convex minimization: a novel approach
- Global convergence of the Heavy-ball method for convex optimization
- Counter-examples in first-order optimization: a constructive approach
- Provable non-accelerations of the heavy-ball method
- Open Problem: Two Riddles in Heavy-Ball Dynamics
- Direct Synthesis of Iterative Algorithms With Bounds on Achievable Worst-Case Convergence Rate
- Analysis and Design of Optimization Algorithms via Integral Quadratic Constraints
- A Lower Bound for the Heavy-Ball Method on Smooth Convex Functions
- Two Answers on Heavy-Ball Dynamics
- The connections between Lyapunov functions for some optimization algorithms and differential equations
- Construction of Periodic Counterexamples to the Discrete-Time Kalman Conjecture
- Understanding the Acceleration Phenomenon via High-Resolution Differential Equations
- An optimal gradient method for smooth strongly convex minimization
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