相关论文: KerZOO: Kernel Function Informed Zeroth-Order Opti…

Large Language Models (LLMs) have demonstrated impressive capabilities in language processing, yet they often struggle with tasks requiring genuine visual spatial reasoning. In this paper, we introduce a novel two-stage training framework…

Single-point zeroth-order optimization (SZO) is useful in solving online black-box optimization and control problems in time-varying environments, as it queries the function value only once at each time step. However, the vanilla SZO method…

Fine-tuning is essential to adapt general-purpose large language models (LLMs) to domain-specific tasks. As a privacy-preserving framework to leverage decentralized data for collaborative model training, Federated Learning (FL) is gaining…

Zeroth-order (ZO) methods are widely used when gradients are unavailable or prohibitively expensive, including black-box learning and memory-efficient fine-tuning of large models, yet their optimization dynamics in deep learning remain…

Large language models (LLMs) have recently emerged as powerful tools for tackling many language-processing tasks. Despite their success, training and fine-tuning these models is still far too computationally and memory intensive. In this…

Gradient descent and backpropagation have enabled neural networks to achieve remarkable results in many real-world applications. Despite ongoing success, training a neural network with gradient descent can be a slow and strenuous affair. We…

Quantization is an effective technique to reduce the deployment cost of large language models (LLMs), and post-training quantization (PTQ) has been widely studied due to its efficiency. However, existing PTQ methods are limited by their…

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Large deep learning models offer significant accuracy gains, but training billions to trillions of parameters is challenging. Existing solutions such as data and model parallelisms exhibit fundamental limitations to fit these models into…

While long-context large language models (LLMs) exhibit remarkable document processing capabilities, their prohibitively high training costs often hinder customized applications. To mitigate this issue, we propose \textit{Sequential…

Gaussian Process (GP) kernels are central to Bayesian optimization (BO), yet designing effective kernels for high-dimensional problems still relies on extensive manual engineering. Existing automated approaches struggle in high dimensions…

In this paper, we consider a stochastic distributed nonconvex optimization problem with the cost function being distributed over $n$ agents having access only to zeroth-order (ZO) information of the cost. This problem has various machine…

Bilevel optimization has emerged as a technique for addressing a wide range of machine learning problems that involve an outer objective implicitly determined by the minimizer of an inner problem. While prior works have primarily focused on…

Large language models (LLMs) have significantly advanced the natural language processing paradigm but impose substantial demands on memory and computational resources. Quantization is one of the most effective ways to reduce memory…

Momentum-Aided Prompt Optimization (MAPO) enhances the efficiency and efficacy of prompt optimization for Large Language Models (LLMs). Building on ProTeGi, MAPO uses positive natural language "gradients" and a momentum-based extension to…

Memory-efficient personalization is critical for adapting text-to-image diffusion models while preserving user privacy and operating within the limited computational resources of edge devices. To this end, we propose a selective…

Training deep computer vision models requires manual oversight or hyperparameter tuning of the learning rate (LR) schedule. While existing adaptive optimizers schedule the LR automatically, they suffer from computational and memory…

This paper introduces an efficient strategy to transform Large Language Models (LLMs) into Multi-Modal Large Language Models (MLLMs). By conceptualizing this transformation as a domain adaptation process, i.e., transitioning from text…

Low-Rank Adaptation (LoRA) is one of the most widely used techniques for fine-tuning large language models (LLMs). By introducing a small number of trainable low-rank weight matrices, LoRA substantially reduces the number of parameters that…

Zeroth-order optimization (ZO) typically relies on two-point feedback to estimate the unknown gradient of the objective function. Nevertheless, two-point feedback can not be used for online optimization of time-varying objective functions,…