Finetuning large language models (LLMs) is a resource-intensive task for researchers in academia, with memory constraints posing a key bottleneck. A classic optimization method, block coordinate descent (BCD), significantly reduces memory cost by segmenting the trainable parameters into multiple blocks and optimizing one active block at a time while freezing the others. However, we identify that blindly applying BCD to train LLMs can be inefficient for two reasons. First, optimizing only the active block requires backpropagating through multiple deeper yet inactive blocks, resulting in wasteful computations. Second, the frozen blocks, when they are not quite close to optimality, can narrow the optimization landscape, potentially misguiding the training of the active block. To address these issues simultaneously, we propose integrating BCD with landscape expansion, which unfreezes the inactive blocks and updates them in a cost-efficient manner during the same backpropagation as the update to the active block. Experiments on 8B and 70B models demonstrate that our proposed method surpasses memory-efficient baselines and matches Adam's downstream performance while requiring only 24 GB of memory for the 8B model and 300 GB for the 70B model.

Finetuning large language models (LLMs) is a resource-intensive task for researchers in academia, with memory constraints posing a key bottleneck. A classic optimization method, block coordinate descent (BCD), significantly reduces memory cost by segmenting the trainable parameters into multiple blocks and optimizing one active block at a time while freezing the others. However, we identify that blindly applying BCD to train LLMs can be inefficient for two reasons. First, optimizing only the active block requires backpropagating through multiple deeper yet inactive blocks, resulting in wasteful computations. Second, the frozen blocks, when they are not quite close to optimality, can narrow the optimization landscape, potentially misguiding the training of the active block. To address these issues simultaneously, we propose integrating BCD with, which unfreezes the inactive blocks and updates them in a cost-efficient manner during the same backpropagation as the update to the active block. Experiments on 8B and 70B models demonstrate that our proposed method surpasses memory-efficient baselines and matches Adam's downstream performance while requiring only 24 GB of memory for the 8B model and 300 GB for the 70B model.

However,asan update ofonlyoneparameter group depends onalltheparameter groups ordata points, the computation cost is high when the number of the parameters or data points islarge. This paper proposes afast Block Coordinate Descent for Sparse GroupLasso.

However,in manyapplications there are several different parameters one might wish to vary: for example, scale and density. In contrast to the one-parameter setting, techniques for applying statistics and machine learning in the setting of multiparameter persistence are not well understood due to the lack of a concise representationoftheresults.

Therefore, it does not suffer from vanishing gradient at all.

LiDAR's dense, sharp point cloud (PC) representations of the surrounding environment enable accurate perception and significantly improve road safety by offering greater scene awareness and understanding. However, LiDAR's high cost continues to restrict the broad adoption of high-level Autonomous Driving (AD) systems in commercially available vehicles. Prior research has shown progress towards circumventing the need for LiDAR by training a neural network, using LiDAR point clouds as ground truth (GT), to produce LiDAR-like 3D point clouds using only 4D Radars. One of the best examples is a neural network created to train a more efficient radar target detector with a modular 2D convolutional neural network (CNN) backbone and a temporal coherence network at its core that uses the RaDelft dataset for training (see arXiv:2406.04723). In this work, we investigate the impact of higher-capacity segmentation backbones on the quality of the produced point clouds. Our results show that while very high-capacity models may actually hurt performance, an optimal segmentation backbone can provide a 23.7% improvement over the state-of-the-art (SOTA).