English
Related papers

Related papers: Online Bayesian Imbalanced Learning with Bregman-C…

200 papers

Uncertainty estimation is critical for cost-sensitive deep-learning applications (i.e. disease diagnosis). It is very challenging partly due to the inaccessibility of uncertainty groundtruth in most datasets. Previous works proposed to…

Machine Learning · Computer Science 2021-10-18 Bolian Li , Zige Zheng , Changqing Zhang

Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost. This approach, known as learning to defer, is essential in domains like natural…

Machine Learning · Computer Science 2026-05-01 Corinna Cortes , Anqi Mao , Mehryar Mohri , Yutao Zhong

Offline reinforcement learning (RL) is challenged by the distributional shift problem. To address this problem, existing works mainly focus on designing sophisticated policy constraints between the learned policy and the behavior policy.…

Machine Learning · Computer Science 2025-01-09 Yang Yue , Bingyi Kang , Xiao Ma , Qisen Yang , Gao Huang , Shiji Song , Shuicheng Yan

Compared to point estimates calculated by standard neural networks, Bayesian neural networks (BNN) provide probability distributions over the output predictions and model parameters, i.e., the weights. Training the weight distribution of a…

Machine Learning · Computer Science 2022-12-01 Philipp Wagner , Xinyang Wu , Marco F. Huber

Comprehending natural language and following human instructions are critical capabilities for intelligent agents. However, the flexibility of linguistic instructions induces substantial ambiguity across language-conditioned tasks, severely…

Artificial Intelligence · Computer Science 2025-10-24 Runpeng Xie , Quanwei Wang , Hao Hu , Zherui Zhou , Ni Mu , Xiyun Li , Yiqin Yang , Shuang Xu , Qianchuan Zhao , Bo XU

Precision medicine is of considerable interest in clinical, academic and regulatory parties. The key to precision medicine is the optimal treatment regime. Recently, Zhou et al. (2017) developed residual weighted learning (RWL) to construct…

Methodology · Statistics 2017-11-30 Xin Zhou , Michael R. Kosorok

We propose a Bayesian approach for recursively estimating the classifier weights in online learning of a classifier ensemble. In contrast with past methods, such as stochastic gradient descent or online boosting, our approach estimates the…

Machine Learning · Computer Science 2015-07-09 Qinxun Bai , Henry Lam , Stan Sclaroff

Measurement of uncertainty of predictions from machine learning methods is important across scientific domains and applications. We present, to our knowledge, the first such technique that quantifies the uncertainty of predictions from a…

Machine Learning · Statistics 2022-04-04 Alex Hagen , Karl Pazdernik , Nicole LaHaye , Marjolein Oostrom

There is an increasing need to determine whether inputs are out-of-distribution (\emph{OOD}) for safely deploying machine learning models in the open world scenario. Typical neural classifiers are based on the closed world assumption, where…

Computer Vision and Pattern Recognition · Computer Science 2022-08-15 Sen Pei , Xin Zhang , Bin Fan , Gaofeng Meng

Deep learning models are considered to be state-of-the-art in many offline machine learning tasks. However, many of the techniques developed are not suitable for online learning tasks. The problem of using deep learning models with…

Machine Learning · Computer Science 2019-05-28 Guy Uziel

We propose a novel online learning algorithm for Restricted Boltzmann Machines (RBM), namely, the Online Generative Discriminative Restricted Boltzmann Machine (OGD-RBM), that provides the ability to build and adapt the network architecture…

Neural and Evolutionary Computing · Computer Science 2018-03-07 Savitha Ramasamy , Kanagasabai Rajaraman , Pavitra Krishnaswamy , Vijay Chandrasekhar

Transfer learning has recently attracted significant research attention, as it simultaneously learns from different source domains, which have plenty of labeled data, and transfers the relevant knowledge to the target domain with limited…

Machine Learning · Statistics 2018-06-14 Alireza Karbalayghareh , Xiaoning Qian , Edward R. Dougherty

Rehearsal approaches in class incremental learning (CIL) suffer from decision boundary overfitting to new classes, which is mainly caused by two factors: insufficiency of old classes data for knowledge distillation and imbalanced data…

Machine Learning · Computer Science 2024-09-27 Kunchi Li , Jun Wan , Shan Yu

Inverse Reinforcement Learning (IRL) is attractive in scenarios where reward engineering can be tedious. However, prior IRL algorithms use on-policy transitions, which require intensive sampling from the current policy for stable and…

Machine Learning · Computer Science 2022-05-24 Hana Hoshino , Kei Ota , Asako Kanezaki , Rio Yokota

Offline (or batch) reinforcement learning (RL) algorithms seek to learn an optimal policy from a fixed dataset without active data collection. Based on the composition of the offline dataset, two main categories of methods are used:…

Machine Learning · Computer Science 2023-07-04 Paria Rashidinejad , Banghua Zhu , Cong Ma , Jiantao Jiao , Stuart Russell

Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large…

Machine Learning · Computer Science 2019-12-05 Xinshao Wang , Yang Hua , Elyor Kodirov , Guosheng Hu , Neil M. Robertson

In multi-objective learning (MOL), several possibly competing prediction tasks must be solved jointly by a single model. Achieving good trade-offs may require a model class $\mathcal{G}$ with larger capacity than what is necessary for…

Machine Learning · Statistics 2025-08-26 Tobias Wegel , Geelon So , Junhyung Park , Fanny Yang

The expansion of machine learning into dynamic environments presents challenges in handling open-world problems where label shift, covariate shift, and unknown classes emerge. Post-training methods have been explored to address these…

Machine Learning · Computer Science 2025-08-26 Miru Kim , Mugon Joe , Minhae Kwon

We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in practice due to mismatches between training and deployment…

Machine Learning · Computer Science 2025-11-12 Debamita Ghosh , George K. Atia , Yue Wang

Incremental Learning (IL) allows AI systems to adapt to streamed data. Most existing algorithms make two strong hypotheses which reduce the realism of the incremental scenario: (1) new data are assumed to be readily annotated when streamed…

Computer Vision and Pattern Recognition · Computer Science 2020-08-26 Eden Belouadah , Adrian Popescu , Umang Aggarwal , Léo Saci