2 citations · 2 across the 4 of their papers we have counts for
5 papers
ATLAS: A Multi-LLM Training Framework for EvoDPO with Adaptive Reference Evolution
Ujin Jeon, Jiyong Kwon, Madison Ann Sullivan +2
Recent multi-LLM agent systems have shown promising capabilities for automated problem-solving, yet they predominantly rely on frozen agents or static fine-tuning pipelines. To add…
Rethinking Langevin Thompson Sampling from A Stochastic Approximation Perspective
Weixin Wang, Haoyang Zheng, Guang Lin +2
Langevin-based Thompson Sampling (TS) methods for multi-armed bandits use likelihood gradients to approximate posterior samples when exact sampling is intractable. As new rewards a…
Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics
Haoyang Zheng, Hengrong Du, Qi Feng +2
Replica exchange stochastic gradient Langevin dynamics (reSGLD) is an effective sampler for non-convex learning in large-scale datasets. However, the simulation may encounter stagn…
Fast Replica Exchange Stochastic Gradient Langevin Dynamics
Guanxun Li, Guang Lin, Zecheng Zhang +1
Application of the replica exchange (i.e., parallel tempering) technique to Langevin Monte Carlo algorithms, especially stochastic gradient Langevin dynamics (SGLD), has scored gre…
Non-reversible Parallel Tempering for Deep Posterior Approximation
Wei Deng, Qian Zhang, Qi Feng +2
Parallel tempering (PT), also known as replica exchange, is the go-to workhorse for simulations of multi-modal distributions. The key to the success of PT is to adopt efficient swa…