REVIEW 10 cited by
Using Large Language Models for Hyperparameter Optimization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
This paper explores the use of foundational large language models (LLMs) in hyperparameter optimization (HPO). Hyperparameters are critical in determining the effectiveness of machine learning models, yet their optimization often relies on manual approaches in limited-budget settings. By prompting LLMs with dataset and model descriptions, we develop a methodology where LLMs suggest hyperparameter configurations, which are iteratively refined based on model performance. Our empirical evaluations on standard benchmarks reveal that within constrained search budgets, LLMs can match or outperform traditional HPO methods like Bayesian optimization across different models on standard benchmarks. Furthermore, we propose to treat the code specifying our model as a hyperparameter, which the LLM outputs and affords greater flexibility than existing HPO approaches.
Forward citations
Cited by 10 Pith papers
-
Agentic Bayesian Optimization through Surrogate-Augmented Autoresearch
An LLM agent that fully controls a reconfigurable Bayesian-optimization backend preserves standard BO reliability, outperforms LLM-only optimizers, and exploits natural-language priors and mid-run problem reformulation.
-
AgentHPOBench: A Benchmark For Evaluating LLM Agents as Sequential Hyperparameter Optimizers
A new 30-task benchmark shows LLM agents can improve real ML experiments through sequential hyperparameter choices, but their gains are uneven and often not retained.
-
Which Optimizer, At What Budget? A Tournament of Optimizers for Search-Based SE
Optimizer choice in search-based SE is budget-dependent (EZR when labels are scarce, DE when plentiful), and a zero-probe table on objective structure and input-space shape predicts the winner ~75% of the time.
-
A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search
LLM embeddings plus Bayesian optimization find better LoRA hyperparameters in ~30 proxy trials than standard published settings.
-
REMoH: A Reflective Evolution of Multi-objective Heuristics approach via Large Language Models
REMoH evolves LLM-written heuristics with NSGA-II and a reflection mechanism, reporting competitive FJSSP results that are weakened by test-set selection.
-
MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
MLZero, an LLM-based multi-agent system with perception and dual memory, reports 92 percent success on a new 25-task multimodal AutoML benchmark and the best average rank on MLE-Bench Lite.
-
DARLR: Dual-Agent Offline Reinforcement Learning for Recommender Systems with Dynamic Reward
DARLR uses a selector agent to pick similar and diverse reference users, then averages their predicted rewards to dynamically refine the reward and uncertainty used to train a recommender policy in offline RL.
-
The Problem of Dynamic Spatial Sampling and Geofence Surveillance
Adaptive geofence radius estimators are proposed to trade off police reverse-location surveillance reach against local privacy under density-aware constraints.
-
Language-Guided Tuning: Enhancing Numeric Optimization with Textual Feedback
A multi-agent LLM framework uses natural-language 'textual gradients' to jointly tune architecture, features, training strategy, and hyperparameters.
-
Advanced For-Loop for QML algorithm search
The paper sketches an LLM-based multi-agent framework that generated quantum variants of MLP, forward-forward, and backpropagation, but with no reproducible evidence that the search works.
Discussion (0). Continue with ORCID to comment.