paper-with-me

홈 › Papers

Non-Vacuous Generalization Bounds for Large Language Models

2023-12-28 · Sanae Lotfi, Marc Finzi, Yilun Kuang, Tim G. J. Rudner, Micah Goldblum, Andrew Gordon Wilson

Modern language models can contain billions of parameters, raising the question of whether they can generalize beyond the training data or simply parrot their training corpora. We provide the first non-vacuous generalization bounds for pretrained large language models (LLMs), indicating that language models are capable of discovering regularities that generalize to unseen data. In particular, we derive a compression bound that is valid for the unbounded log-likelihood loss using prediction smoothing, and we extend the bound to handle subsampling, accelerating bound computation by orders of magnitude on massive datasets. To achieve the extreme level of compression required for non-vacuous bounds, we devise SubLoRA, a simple low-dimensional nonlinear parameterization that leads to non-vacuous generalization bounds for models with nearly a billion parameters. Finally, we use our bounds to understand LLM generalization and find that larger models have better generalization bounds and are more compressible than smaller models.

📄 PDF Abstract BibTeX arXiv:2312.17173

Code (1)

sanaelotfi/sublora-bounds-for-llms 공식 구현 pytorch

Tasks

Generalization Boundsvalid

Similar Papers 제목 키워드 기반

Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models

2024-07-25 · Sanae Lotfi, Yilun Kuang, Brandon Amos, Micah Goldblum 외

Large language models (LLMs) with billions of parameters excel at predicting the next token in a sequence. Recent work computes non-vacuous compression-based generalization bounds for LLMs, but these bounds are vacuous f…

Generalization BoundsQuantization

A Generalization Bound for Nearly-Linear Networks

2024-07-09 · Eugene Golikov

We consider nonlinear networks as perturbations of linear ones. Based on this approach, we present novel generalization bounds that become non-vacuous for networks that are close to being linear. The main advantage over …

Generalization Bounds

Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards

2026-07-16 · Yuxuan Zhu, Rohan Alur, Daniel Kang arxiv

While reinforcement learning with verifiable rewards (RLVR) is widely used to improve the reasoning capabilities of large language models (LLMs), the generalizability of the resulting models remains poorly understood. In…

Reinforcement Learning

Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data

2017-03-31 · Gintare Karolina Dziugaite, Daniel M. Roy

One of the defining properties of deep learning is that models are chosen to have many more parameters than available training data. In light of this capacity for overfitting, it is remarkable that simple algorithms like…

Generalization Bounds

Prompts Generalize with Low Data: Non-vacuous Generalization Bounds for Optimizing Prompts with More Informative Priors

2025-10-09 · David Madras, Joshua Safyan, Qiuyi, Zhang arxiv

Many prompt engineering techniques have been successful in practice, even when optimizing over a large prompt space with with a small amount of task-specific data. Recent work has partially explained this success by show…

Prompt Engineering