Search Results for author:
Found 10 papers, 4 papers with code
MoFO: Momentum-Filtered Optimizer for Mitigating Forgetting in LLM Fine-Tuning
This could avoid impairing the model performance on the fine-tuning tasks.
Adam-mini: Use Fewer Learning Rates To Gain More
Adam-mini reduces memory by cutting down the learning rate resources in Adam (i. e., $1/\sqrt{v}$).
Why Transformers Need Adam: A Hessian Perspective
SGD performs worse than Adam by a significant margin on Transformers, but the reason remains unclear.
Communication Efficiency Optimization of Federated Learning for Computing and Network Convergence of 6G Networks
In this paper, to improve the communication efficiency of federated learning in complex networks, we study the communication efficiency optimization of federated learning for computing and network convergence of 6G networks, methods that gives decisions on its training process for different network conditions and arithmetic power of participating devices in federated learning.
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models
ReMax can save about 46% GPU memory than PPO when training a 7B model and enables training on A800-80GB GPUs without the memory-saving offloading technique needed by PPO.
Uncertainty and Explainable Analysis of Machine Learning Model for Reconstruction of Sonic Slowness Logs
Using the SHAP explainable machine learning model, we calculate the importance of each input log to the predicted results as well as the coupling relationship among input logs.
When Expressivity Meets Trainability: Fewer than $n$ Neurons Can Work
Third, we consider a constrained optimization formulation where the feasible region is the nice local region, and prove that every KKT point is a nearly global minimizer.
Provable Adaptivity of Adam under Non-uniform Smoothness
We present the first convergence analysis of RR Adam without the bounded smoothness assumption.
Adam Can Converge Without Any Modification On Update Rules
We point out there is a mismatch between the settings of theory and practice: Reddi et al. 2018 pick the problem after picking the hyperparameters of Adam, i. e., $(\beta_1, \beta_2)$; while practical applications often fix the problem first and then tune $(\beta_1, \beta_2)$.
HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning
However, it is limited to the case where 1) a good feature is known in advance and 2) this feature is fixed during the training: if otherwise, RLSVI suffers an unbearable computational burden to obtain the posterior samples of the parameter in the $Q$-value function.
