What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research Agents
Reusing a held-out benchmark adaptively should, in principle, invite overfitting. Yet benchmark-driven machine learning (ML) has produced surprisingly little overfitting in practice. An attractive hypothesis is that successful ML strategies are highly compressible. We study this in the setting of LLM-driven research agents, where the hypothesis becomes directly testable via two complementary information bottlenecks. In \emph{output compression}, an exploration agent adaptively searches for high-performance models using a validation set, and we test whether a fresh ``reproducer agent'' can reproduce its performance given only an extremely short prompt and the training data. In \emph{input compression}, the explorer receives only one-bit feedback indicating whether each submitted model improves on the running best. Across 8 datasets spanning tabular classification, vision, language modeling, diffusion modeling, and reward modeling, we find that these bottlenecks have little effect on performance: short prompts and compressible feedback are sufficient to reproduce and find high-performance models. The hypothesis is falsifiable: when we deliberately induce validation-set overfitting, the results fail to reproduce with short prompts. Taken together, our results support a description-length explanation for the lack of overfitting in benchmark-driven ML: successful strategies occupy a low-complexity region of strategy space.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
Multimodal language models (MLMs) still face challenges in fundamental visual perception tasks where specialized models excel. Tasks requiring reasoning about 3D structures benefit from depth estimation, and reasoning ab…
Depth Estimationobject-detectionObject DetectionVisual ReasoningAnalogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn't.
Benign Overfitting in Single-Head Attention
The phenomenon of benign overfitting, where a trained neural network perfectly fits noisy training data but still achieves near-optimal test performance, has been extensively studied in recent years for linear models and…
On the Benefits of Over-parameterization for Out-of-Distribution Generalization
In recent years, machine learning models have achieved success based on the independently and identically distributed assumption. However, this assumption can be easily violated in real-world applications, leading to the…
Out-of-Distribution GeneralizationLearning and Generalization in Overparameterized Neural Networks, Going Beyond Two Layers
The fundamental learning theory behind neural networks remains largely open. What classes of functions can neural networks actually learn? Why doesn't the trained network overfit when it is overparameterized? In this wor…
Learning TheoryVocal Bursts Valence Prediction