The widespread practice of fine-tuning pretrained large language models (LLMs) on domain-specific data faces two major challenges in memory and privacy. First, as the size of LLMs continue to grow, encompassing billions of parameters, the memory demands of gradient-based training methods via backpropagation become prohibitively high. Second, given the tendency of LLMs to memorize and disclose sensitive training data, the privacy of fine-tuning data must be respected. To this end, we explore the potential of zeroth-order methods in differentially private optimization for fine-tuning LLMs. Zeroth-order methods, which rely solely on forward passes, substantially reduce memory consumption during training. However, directly combining them with standard differential privacy mechanism poses dimension-dependent complexity. To bridge the gap, we introduce DPZero, a novel differentially private zeroth-order algorithm with nearly dimension-independent rates. Our theoretical analysis reveals that its complexity hinges primarily on the problem's intrinsic dimension and exhibits only a logarithmic dependence on the ambient dimension. This renders DPZero a highly practical option for real-world LLMs deployments.
翻译:暂无翻译