Search:
Match:
1 results

Analysis

This paper investigates the Lottery Ticket Hypothesis (LTH) in the context of parameter-efficient fine-tuning (PEFT) methods, specifically Low-Rank Adaptation (LoRA). It finds that LTH applies to LoRAs, meaning sparse subnetworks within LoRAs can achieve performance comparable to dense adapters. This has implications for understanding transfer learning and developing more efficient adaptation strategies.
Reference

The effectiveness of sparse subnetworks depends more on how much sparsity is applied in each layer than on the exact weights included in the subnetwork.