Llm Based Gradient Free Optimization Via In Context Learning

via “llm-based gradient-free optimization via in-context learning”

* ⏫ 10/2023: [Eureka: Human-Level Reward Design via Coding Large Language Models (Eureka)](https://arxiv.org/abs/2310.12931)

Unique: Treats optimization as an in-context learning problem where the LLM infers optimization dynamics from trajectory history rather than using explicit gradient signals or learned surrogate models. The key architectural insight is that LLMs can act as meta-optimizers by recognizing patterns in (solution, score) pairs and generating better candidates without domain-specific training.

vs others: Outperforms traditional Bayesian optimization and evolutionary algorithms on discrete/non-differentiable problems by leveraging LLM's semantic understanding of solution space structure, while requiring no gradient computation or surrogate model training.

via “optimization-algorithm-implementation”

A guide to building your own working LLM, by Sebastian Raschka.

Unique: Implements optimization algorithms from scratch, showing how momentum accumulates gradients and how adaptive learning rates (Adam) maintain per-parameter learning rate estimates, with explicit state management

vs others: More educational than using framework optimizers directly, enabling practitioners to understand and modify optimization behavior for specific training scenarios

via “gradient-descent-algorithm-teaching”