English
Related papers

Related papers: Dynamic Update-to-Data Ratio: Minimizing World Mod…

200 papers

Reinforcement finetuning (RFT) has shown great potential for enhancing the mathematical reasoning capabilities of large language models (LLMs), but it is often sample- and compute-inefficient, requiring extensive training. In this work, we…

Machine Learning · Computer Science 2026-02-03 Taiwei Shi , Yiyang Wu , Linxin Song , Tianyi Zhou , Jieyu Zhao

Policy optimization in reinforcement learning requires the selection of numerous hyperparameters across different environments. Fixing them incorrectly may negatively impact optimization performance leading notably to insufficient or…

Robotics · Computer Science 2021-03-26 Jiancong Huang , Juan Rojas , Matthieu Zimmer , Hongmin Wu , Yisheng Guan , Paul Weng

Reinforcement learning is structurally harder than supervised learning because the policy changes the data distribution it learns from. The resulting fragility is especially visible in large-model training, where the training and rollout…

Machine Learning · Computer Science 2026-05-13 Rasool Fakoor , Murdock Aubry , Nicholas Stranges , Alexander J. Smola

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Machine Learning · Computer Science 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang

Although reinforcement learning methods can achieve impressive results in simulation, the real world presents two major challenges: generating samples is exceedingly expensive, and unexpected perturbations or unseen situations cause…

Machine Learning · Computer Science 2019-03-01 Anusha Nagabandi , Ignasi Clavera , Simin Liu , Ronald S. Fearing , Pieter Abbeel , Sergey Levine , Chelsea Finn

Unsupervised domain adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain by addressing domain shifts. Most UDA approaches emphasize transfer ability, but often overlook robustness against…

Machine Learning · Computer Science 2025-11-17 Fuxiang Huang , Xiaowei Fu , Shiyu Ye , Lina Ma , Wen Li , Xinbo Gao , David Zhang , Lei Zhang

Continual learning aims to acquire new tasks while preserving performance on previously learned ones, but most methods struggle with catastrophic forgetting. Existing approaches typically treat all layers uniformly, often trading stability…

Machine Learning · Computer Science 2025-12-29 Hengyi Wu , Zhenyi Wang , Heng Huang

As numerous instruction-tuning datasets continue to emerge during the post-training stage, dynamically balancing and optimizing their mixtures has become a critical challenge. To address this, we propose DynamixSFT, a dynamic and automated…

Machine Learning · Computer Science 2025-08-19 Haebin Shin , Lei Ji , Xiao Liu , Zhiwei Yu , Qi Chen , Yeyun Gong

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

Computer Vision and Pattern Recognition · Computer Science 2025-01-27 Haoran Chen , Micah Goldblum , Zuxuan Wu , Yu-Gang Jiang

Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. This problem usually arises due to the overfitting problem, which is characterized by learning everything presented in the…

Machine Learning · Computer Science 2024-07-16 Zongbo Han , Yifeng Yang , Changqing Zhang , Linjun Zhang , Joey Tianyi Zhou , Qinghua Hu

In this paper, we propose a new method called Self-Training with Dynamic Weighting (STDW), which aims to enhance robustness in Gradual Domain Adaptation (GDA) by addressing the challenge of smooth knowledge migration from the source to the…

Machine Learning · Computer Science 2025-10-17 Zixi Wang , Yushe Cao , Yubo Huang , Jinzhu Wei , Jingzehua Xu , Shuai Zhang , Xin Lai

Changes to hyperparameters can have a dramatic effect on model accuracy. Thus, the tuning of hyperparameters plays an important role in optimizing machine-learning models. An integral part of the hyperparameter-tuning process is the…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Kevin Musgrave , Serge Belongie , Ser-Nam Lim

Unsupervised domain adaptation (UDA) aims to mitigate the domain shift issue, where the distribution of training (source) data differs from that of testing (target) data. Many models have been developed to tackle this problem, and recently…

Computer Vision and Pattern Recognition · Computer Science 2024-08-01 Ali Abedi , Q. M. Jonathan Wu , Ning Zhang , Farhad Pourpanah

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In…

Machine Learning · Computer Science 2023-10-30 Thomas Schmied , Markus Hofmarcher , Fabian Paischer , Razvan Pascanu , Sepp Hochreiter

We propose adaptive weight decay, which automatically tunes the hyper-parameter for weight decay during each training iteration. For classification problems, we propose changing the value of the weight decay hyper-parameter on the fly based…

Machine Learning · Computer Science 2023-12-05 Amin Ghiasi , Ali Shafahi , Reza Ardekani

The \textit{de facto} paradigm for applying dense retrieval (DR) to new tasks involves fine-tuning a pre-trained model for a specific task. However, this paradigm has two significant limitations: (1) It is difficult adapt the DR to a new…

Information Retrieval · Computer Science 2026-02-27 Zhan Su , Fengran Mo , Jinghan Zhang , Yuchen Hui , Jia Ao Sun , Bingbing Wen , Jian-Yun Nie

Controlling artificial agents from visual sensory data is an arduous task. Reinforcement learning (RL) algorithms can succeed but require large amounts of interactions between the agent and the environment. To alleviate the issue,…

Artificial Intelligence · Computer Science 2023-05-26 Sai Rajeswar , Pietro Mazzaglia , Tim Verbelen , Alexandre Piché , Bart Dhoedt , Aaron Courville , Alexandre Lacoste

Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and supervised training for…

Computer Vision and Pattern Recognition · Computer Science 2023-05-24 Emirhan Kurtulus , Zichao Li , Yann Dauphin , Ekin Dogus Cubuk

Data augmentation has proved extremely useful by increasing training data variance to alleviate overfitting and improve deep neural networks' generalization performance. In medical image analysis, a well-designed augmentation policy usually…

Computer Vision and Pattern Recognition · Computer Science 2021-03-31 Yunhe Gao , Zhiqiang Tang , Mu Zhou , Dimitris Metaxas

Traditional approaches in offline reinforcement learning aim to learn the optimal policy that maximizes the cumulative reward, also known as return. It is increasingly important to adjust the performance of AI agents to meet human…

Machine Learning · Computer Science 2025-06-23 Tsunehiko Tanaka , Kenshi Abe , Kaito Ariu , Tetsuro Morimura , Edgar Simo-Serra
‹ Prev 1 3 4 5 6 7 10 Next ›