Fine-Tuning Language Models with Just Forward Passes
Paper
•
2305.17333
•
Published
•
3
No backprop
-
-
HyperTuning: Toward Adapting Large Language Models without Back-propagation
Paper • 2211.12485 • Published • 1 -
Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude Pruning
Paper • 2209.14624 • Published • 1 -
Backpropagation-free Training of Deep Physical Neural Networks
Paper • 2304.11042 • Published • 1 -
Lottery Tickets in Evolutionary Optimization: On Sparse Backpropagation-Free Trainability
Paper • 2306.00045 • Published • 1 -
Gradients without Backpropagation
Paper • 2202.08587 • Published • 1 -
Learning with Local Gradients at the Edge
Paper • 2208.08503 • Published • 1 -
ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization
Paper • 2312.15184 • Published • 1 -
DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training
Paper • 2310.02025 • Published • 1 -
AdaZeta: Adaptive Zeroth-Order Tensor-Train Adaption for Memory-Efficient Large Language Models Fine-Tuning
Paper • 2406.18060 • Published -
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity
Paper • 2406.02913 • Published -
BBTv2: Towards a Gradient-Free Future with Large Language Models
Paper • 2205.11200 • Published -
Enhancing Zeroth-order Fine-tuning for Language Models with Low-rank Structures
Paper • 2410.07698 • Published -
ZOQO: Zero-Order Quantized Optimization
Paper • 2501.06736 • Published -
Subspace-based Approximate Hessian Method for Zeroth-Order Optimization
Paper • 2507.06125 • Published