English
Related papers

Related papers: Early-stopping for Transformer model training

200 papers

Preference-based reinforcement learning (PbRL) has emerged as a promising paradigm for teaching robots complex behaviors without reward engineering. However, its effectiveness is often limited by two critical challenges: the reliance on…

Robotics · Computer Science 2025-12-02 Ruiqi Wang , Dezhong Zhao , Ziqin Yuan , Tianyu Shao , Guohua Chen , Dominic Kao , Sungeun Hong , Byung-Cheol Min

This thesis addresses two persistent and closely related challenges in modern deep learning, reliability and efficiency, through a unified framework grounded in Spectral Geometry and Random Matrix Theory (RMT). As deep networks and large…

Machine Learning · Computer Science 2026-02-27 Davide Ettori

Gradient signals in LLM training are highly anisotropic: recurrent linguistic structure concentrates energy into a small set of dominant spectral directions, while context specific information resides in a long tail. We show that this spike…

Dynamic Rank Reinforcement Learning (DR-RL) approximations rely on static rank assumptions, limiting their flexibility across diverse linguistic contexts. Our method dynamically modulates ranks based on real-time sequence dynamics,…

Machine Learning · Computer Science 2026-02-10 Caner Erden

We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where firstly, we approximate a model from Model-Free reinforcement learning. Then, we…

Machine Learning · Computer Science 2019-01-09 Shoubhik Debnath , Gaurav Sukhatme , Lantao Liu

Reinforcement Learning (RL) has emerged as an efficient method of choice for solving complex sequential decision making problems in automatic control, computer science, economics, and biology. In this paper we present a model-free RL…

Logic in Computer Science · Computer Science 2019-09-13 Mohammadhosein Hasanbeig , Yiannis Kantaros , Alessandro Abate , Daniel Kroening , George J. Pappas , Insup Lee

Early stopping based on the validation set performance is a popular approach to find the right balance between under- and overfitting in the context of supervised learning. However, in reinforcement learning, even for supervised…

Machine Learning · Computer Science 2023-03-20 Nicolai Dorka , Tim Welschehold , Wolfram Burgard

Model-based reinforcement learning could enable sample-efficient learning by quickly acquiring rich knowledge about the world and using it to improve behaviour without additional data. Learned dynamics models can be directly used for…

Machine Learning · Computer Science 2019-10-15 Rinu Boney , Juho Kannala , Alexander Ilin

Reinforcement learning (RL) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). While RL has demonstrated substantial performance gains, it still faces key challenges, including low…

Machine Learning · Computer Science 2025-11-18 Yihang Yao , Guangtao Zeng , Raina Wu , Yang Zhang , Ding Zhao , Zhang-Wei Hong , Chuang Gan

General-purpose control demands agents that act across many tasks and embodiments, yet research on reinforcement learning (RL) for continuous control remains dominated by single-task or offline regimes, reinforcing a view that online RL…

Machine Learning · Computer Science 2025-12-03 Nicklas Hansen , Hao Su , Xiaolong Wang

This thesis focuses on improving the pre-training of natural language models using unsupervised raw data to make them more efficient and aligned with downstream applications. In the first part, we introduce three alternative pre-training…

Computation and Language · Computer Science 2023-09-18 Luca Di Liello

We apply Tsallis's q-indexed nonextensive entropy to formulate a random matrix theory (RMT), which may be suitable for systems with mixed regular-chaotic dynamics. We consider the super-extensive regime of q < 1. We obtain analytical…

Mathematical Physics · Physics 2011-12-06 A. Abd El-Hady , A. Y. Abul-Magd

Empirical studies of trained models often report a transient regime in which signal is detectable in a finite gradient descent time window before overfitting dominates. We provide an analytically tractable random-matrix model that…

Machine Learning · Statistics 2026-04-21 Florentin Coeurdoux , Grégoire Ferré , Jean-Philippe Bouchaud

In real-world scenarios, where knowledge distributions exhibit long-tail. Humans manage to master knowledge uniformly across imbalanced distributions, a feat attributed to their diligent practices of reviewing, summarizing, and correcting…

Computer Vision and Pattern Recognition · Computer Science 2024-09-16 Qihao Zhao , Yalun Dai , Shen Lin , Wei Hu , Fan Zhang , Jun Liu

The ability to accurately predict feasible multimodal future trajectories of surrounding traffic participants is crucial for behavior planning in autonomous vehicles. The Motion Transformer (MTR), a state-of-the-art motion prediction…

Traffic signal control has a great impact on alleviating traffic congestion in modern cities. Deep reinforcement learning (RL) has been widely used for this task in recent years, demonstrating promising performance but also facing many…

Artificial Intelligence · Computer Science 2024-04-02 Liwen Zhu , Peixi Peng , Zongqing Lu , Yonghong Tian

Transformer, originally devised for natural language processing, has also attested significant success in computer vision. Thanks to its super expressive power, researchers are investigating ways to deploy transformers to reinforcement…

Machine Learning · Computer Science 2023-01-24 Shengchao Hu , Li Shen , Ya Zhang , Yixin Chen , Dacheng Tao

The fine-tuning paradigm has emerged as a prominent approach for addressing long-tail learning tasks in the era of foundation models. However, the impact of fine-tuning strategies on long-tail learning performance remains unexplored. In…

Computer Vision and Pattern Recognition · Computer Science 2025-04-21 Jiang-Xin Shi , Tong Wei , Yu-Feng Li

In the field of autonomous driving, there have been many excellent perception models for object detection, semantic segmentation, and other tasks, but how can we effectively use the perception models for vehicle planning? Traditional…

Robotics · Computer Science 2023-08-04 Jingyu Du , Yang Zhao , Hong Cheng

In previous research, we developed methods to train decision trees (DT) as agents for reinforcement learning tasks, based on deep reinforcement learning (DRL) networks. The samples from which the DTs are built, use the environment's state…

Machine Learning · Computer Science 2024-12-09 Raphael C. Engelhardt , Marcel J. Meinen , Moritz Lange , Laurenz Wiskott , Wolfgang Konen
‹ Prev 1 8 9 10 Next ›