Improved Convergence Rates for Stochastic Multi-Gradient Descent which Close the Gap: A Proof by AI
math.OC, cs.AI, cs.LG
Submitted: 2026-07-20
Updated: 2026-09-06
Terminology
Sources
- Early science acceleration experiments with GPT-5
- Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond
- Regularity-Aware Stochastic MGDA with Adaptive Per-Iterate Conflict-Avoidant Update
- Point Convergence of Nesterov's Accelerated Gradient Method: An AI-Assisted Proof
- AI-Assisted Discovery of Convex Relaxations via Dual Agents
- Last-Iterate Convergence of Optimistic Multiplicative Weight Update
- Accelerating mathematical research with language models: A case study of an interaction with GPT-5-Pro on a convex analysis problem
Related papers
- An Accelerated Proximal Gradient Method for Bures-Wasserstein Space
- FOMTools: Development and AI-Assisted Code Generation for First-Order Methods
- Lions and Muons: Optimization via Stochastic Frank-Wolfe under Heavy-Tailed Noise
- Dynamic Service Recommendation with Congestion-Dependent Joining: Near-Optimal and Constant-Factor Approximation Algorithms
- Integrating Learning and Optimization for Open Transport Capacity Pooling under Disruption
- Zeroth-Order Gradient Estimators under Decision-Dependent Noise