Zobrazeno 1 - 10
of 2 948
pro vyhledávání: '"GU Bin"'
The growing use of large language models (LLMs) has raised concerns regarding their safety. While many studies have focused on English, the safety of LLMs in Arabic, with its linguistic and cultural complexities, remains under-explored. Here, we aim
Externí odkaz:
http://arxiv.org/abs/2410.17040
Publikováno v:
Neural Computation, 2024, 36(5): 897-935
Zeroth-order (ZO) optimization is one key technique for machine learning problems where gradient calculation is expensive or impossible. Several variance reduced ZO proximal algorithms have been proposed to speed up ZO optimization for non-smooth pro
Externí odkaz:
http://arxiv.org/abs/2410.02559
Publikováno v:
International Conference on Machine Learning. PMLR, 2022: 19935-19955
Zeroth-order (ZO) method has been shown to be a powerful method for solving the optimization problem where explicit expression of the gradients is difficult or infeasible to obtain. Recently, due to the practical value of the constrained problems, a
Externí odkaz:
http://arxiv.org/abs/2409.00459
Publikováno v:
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:44838-44864, 2024
Bilevel optimization (BO) has recently gained prominence in many machine learning applications due to its ability to capture the nested structure inherent in these problems. Recently, many hypergradient methods have been proposed as effective solutio
Externí odkaz:
http://arxiv.org/abs/2406.17386
Evolution Strategies (ES) have emerged as a competitive alternative for model-free reinforcement learning, showcasing exemplary performance in tasks like Mujoco and Atari. Notably, they shine in scenarios with imperfect reward functions, making them
Externí odkaz:
http://arxiv.org/abs/2405.01615
Large language models (LLMs) has experienced exponential growth, they demonstrate remarkable performance across various tasks. Notwithstanding, contemporary research primarily centers on enhancing the size and quality of pretraining data, still utili
Externí odkaz:
http://arxiv.org/abs/2404.08885
Continuous graph neural networks (CGNNs) have garnered significant attention due to their ability to generalize existing discrete graph neural networks (GNNs) by introducing continuous dynamics. They typically draw inspiration from diffusion-based me
Externí odkaz:
http://arxiv.org/abs/2404.01897
Spiking Neural Networks (SNNs) offer a promising avenue for energy-efficient computing compared with Artificial Neural Networks (ANNs), closely mirroring biological neural processes. However, this potential comes with inherent challenges in directly
Externí odkaz:
http://arxiv.org/abs/2403.18388
Recent statements about the impressive capabilities of large language models (LLMs) are usually supported by evaluating on open-access benchmarks. Considering the vast size and wide-ranging sources of LLMs' training data, it could explicitly or impli
Externí odkaz:
http://arxiv.org/abs/2402.15938
Autor:
Li, Loka, Ng, Ignavier, Luo, Gongxu, Huang, Biwei, Chen, Guangyi, Liu, Tongliang, Gu, Bin, Zhang, Kun
Conventional causal discovery methods rely on centralized data, which is inconsistent with the decentralized nature of data in many real-world situations. This discrepancy has motivated the development of federated causal discovery (FCD) approaches.
Externí odkaz:
http://arxiv.org/abs/2402.13241