English
Related papers

Related papers: AIS: Adaptive Importance Sampling for Quantized RL

200 papers

Reinforcement learning (RL) has shown great promise in large language models (LLMs) post-training, which typically rely on token-level clipping to maintain stability during optimization. Despite the empirical success of GRPO-style methods,…

Computation and Language · Computer Science 2026-05-18 Jiakang Wang , Runze Liu , Qingpeng Cai , Lei Lin , Wenping Hu , Xiu Li , Fuzheng Zhang , Guorui Zhou , Kun Gai , Ling Pan

Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence lengths make attention and KV-cache memory dominate end-to-end step time. FP8 offers an attractive…

Machine Learning · Computer Science 2026-04-13 Zhaopeng Qiu , Shuang Yu , Jingqi Zhang , Shuai Zhang , Xue Huang , Jingyi Yang , Junjie Lai

Reinforcement learning (RL) fine-tuning of large language models (LLMs) often suffers from instability due to the numerical mismatch between the training and inference policies. While prior work has attempted to mitigate this issue through…

Machine Learning · Computer Science 2025-10-31 Penghui Qi , Zichen Liu , Xiangxin Zhou , Tianyu Pang , Chao Du , Wee Sun Lee , Min Lin

Stochastic sampling algorithms, while an attractive alternative to exact algorithms in very large Bayesian network models, have been observed to perform poorly in evidential reasoning with extremely unlikely evidence. To address this…

Artificial Intelligence · Computer Science 2011-06-02 J. Cheng , M. J. Druzdzel

The machine learning community has witnessed impressive advancements since large language models (LLMs) first appeared. Yet, their massive memory consumption has become a significant roadblock to large-scale training. For instance, a 7B…

Machine Learning · Computer Science 2024-12-30 Rui Pan , Xiang Liu , Shizhe Diao , Renjie Pi , Jipeng Zhang , Chi Han , Tong Zhang

Importance sampling (IS) is a Monte Carlo methodology that allows for approximation of a target distribution using weighted samples generated from another proposal distribution. Adaptive importance sampling (AIS) implements an iterative…

Computation · Statistics 2018-06-04 Yousef El-Laham , Victor Elvira , Monica F. Bugallo

Annealed Importance Sampling (AIS) synthesizes weighted samples from an intractable distribution given its unnormalized density function. This algorithm relies on a sequence of interpolating distributions bridging the target to an initial…

Machine Learning · Statistics 2023-06-28 Shirin Goshtasbpour , Victor Cohen , Fernando Perez-Cruz

Reinforcement learning (RL) for large language model reasoning is frequently hindered by signal loss, a phenomenon where standard uniform sampling with small group sizes fails to uncover informative learning signals for difficult prompts.…

Machine Learning · Computer Science 2025-12-08 Wei Xiong , Chenlu Ye , Baohao Liao , Hanze Dong , Xinxing Xu , Christof Monz , Jiang Bian , Nan Jiang , Tong Zhang

Adaptive importance sampling (AIS) algorithms are a rising methodology in signal processing, statistics, and machine learning. An effective adaptation of the proposals is key for the success of AIS. Recent works have shown that gradient…

Computation · Statistics 2025-03-27 Víctor Elvira , Émilie Chouzenoux , O. Deniz Akyildiz

Probabilistic models based on Restricted Boltzmann Machines (RBMs) imply the evaluation of normalized Boltzmann factors, which in turn require from the evaluation of the partition function Z. The exact evaluation of Z, though, becomes a…

Machine Learning · Computer Science 2020-07-24 Ferran Mazzanti , Enrique Romero

Reinforcement learning exhibits potential in enhancing the reasoning abilities of large language models, yet it is hard to scale for the low sample efficiency during the rollout phase. Existing methods attempt to improve efficiency by…

Machine Learning · Computer Science 2026-02-02 Deyang Kong , Qi Guo , Xiangyu Xi , Wei Wang , Jingang Wang , Xunliang Cai , Shikun Zhang , Wei Ye

Adaptive importance sampling (AIS) algorithms are widely used to approximate expectations with respect to complicated target probability distributions. When the target has heavy tails, existing AIS algorithms can provide inconsistent…

Computation · Statistics 2023-10-26 Thomas Guilmeau , Nicola Branchini , Emilie Chouzenoux , Víctor Elvira

In importance sampling (IS)-based reinforcement learning algorithms such as Proximal Policy Optimization (PPO), IS weights are typically clipped to avoid large variance in learning. However, policy update from clipped statistics induces…

Machine Learning · Computer Science 2019-05-30 Seungyul Han , Youngchul Sung

Direct Alignment Algorithms (DAAs) such as Direct Preference Optimization (DPO) have emerged as alternatives to the standard Reinforcement Learning from Human Feedback (RLHF) for aligning large language models (LLMs) with human values.…

Machine Learning · Computer Science 2025-06-12 Phuc Minh Nguyen , Ngoc-Hieu Nguyen , Duy H. M. Nguyen , Anji Liu , An Mai , Binh T. Nguyen , Daniel Sonntag , Khoa D. Doan

We study robust high-dimensional sparse regression under finite-variance heavy-tailed noise, epsilon-contamination, and alpha-mixing dependence via two subsampling estimators: Adaptive Importance Sampling (AIS) and Stratified Sub-sampling…

Statistics Theory · Mathematics 2026-03-11 Prateek Mittal , Joohi Chauhan

Reinforcement learning, including reinforcement learning with verifiable rewards (RLVR), has emerged as a powerful approach for LLM post-training. Central to these approaches is the design of the importance sampling (IS) ratio used in…

Machine Learning · Computer Science 2026-05-11 Yuheng Zhang , Chenlu Ye , Shuowei Jin , Changlong Yu , Wei Xiong , Saurabh Sahu , Nan Jiang

Reinforcement Learning with Verifiable Reward (RLVR) is a powerful method for enhancing the reasoning abilities of Large Language Models, but its full potential is limited by a lack of exploration in two key areas: Depth (the difficulty of…

Machine Learning · Computer Science 2026-04-14 Zhicheng Yang , Zhijiang Guo , Yinya Huang , Yongxin Wang , Dongchun Xie , Hanhui Li , Yiwei Wang , Xiaodan Liang , Jing Tang

Bayesian neural networks (BNNs) have received an increased interest in the last years. In BNNs, a complete posterior distribution of the unknown weight and bias parameters of the network is produced during the training stage. This…

Machine Learning · Computer Science 2023-04-14 Yunshi Huang , Emilie Chouzenoux , Victor Elvira , Jean-Christophe Pesquet

The widespread adoption of large language models (LLMs) across industries has increased the demand for high-quality and customizable outputs. However, traditional alignment methods often require retraining large pretrained models, making it…

Computation and Language · Computer Science 2025-12-16 Yi Liu , Dianqing Liu , Mingye Zhu , Junbo Guo , Yongdong Zhang , Zhendong Mao

Aligning Large Language Models (LLMs) to cater to different human preferences, learning new skills, and unlearning harmful behavior is an important problem. Search-based methods, such as Best-of-N or Monte-Carlo Tree Search, are performant,…

Machine Learning · Computer Science 2024-05-13 Seungwook Han , Idan Shenfeld , Akash Srivastava , Yoon Kim , Pulkit Agrawal
‹ Prev 1 2 3 10 Next ›