Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuning

TL;DR

This paper demonstrates that random masking during fine-tuning large language models can match the performance of more complex parameter-efficient methods, using fewer trainable parameters and larger learning rates.

Contribution

It introduces Random Masking as a simple yet effective method for parameter-efficient fine-tuning, with empirical and theoretical analysis of its advantages.

Findings

Random Masking matches standard PEFT performance on various tasks.

Masking induces a flatter loss landscape and distant solutions.

Large learning rates are effective with Random Masking.

Abstract

Fine-tuning large language models (LLM) can be costly. Parameter-efficient fine-tuning (PEFT) addresses the problems by training a fraction of the parameters, whose success reveals the expressiveness and flexibility of pretrained models. This paper studies the limit of PEFT, by further simplifying its design and reducing the number of trainable parameters beyond standard setups. To this end, we use Random Masking to fine-tune the pretrained model. Despite its simplicity, we show that Random Masking is surprisingly effective: with a larger-than-expected learning rate, Random Masking can match the performance of standard PEFT algorithms such as LoRA on various tasks, using fewer trainable parameters. We provide both empirical and theoretical explorations into the success of Random Masking. We show that masking induces a flatter loss landscape and more distant solutions, which allows for and necessitates large learning rates.