English
Related papers

Related papers: New Insights on Relieving Task-Recency Bias for On…

200 papers

Regularized online learning is widely used in machine learning applications. In online learning, performing exact minimization ($i.e.,$ implicit update) is known to be beneficial to the numerical stability and structure of solution. In this…

Machine Learning · Computer Science 2019-02-08 Chaobing Song , Ji Liu , Han Liu , Yong Jiang , Tong Zhang

Class-incremental learning aims to learn new classes in an incremental fashion without forgetting the previously learned ones. Several research works have shown how additional data can be used by incremental models to help mitigate…

Machine Learning · Computer Science 2023-10-11 Quentin Jodelet , Xin Liu , Yin Jun Phua , Tsuyoshi Murata

Class-incremental learning (CIL) aims to enable models to continuously learn new classes while overcoming catastrophic forgetting. The introduction of pre-trained models has brought new tuning paradigms to CIL. In this paper, we revisit…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Qinhao Zhou , Yuwen Tan , Boqing Gong , Xiang Xiang

Importance sampling (IS) is a popular technique in off-policy evaluation, which re-weights the return of trajectories in the replay buffer to boost sample efficiency. However, training with IS can be unstable and previous attempts to…

Machine Learning · Computer Science 2025-05-20 Chengyang Ying , Zhongkai Hao , Xinning Zhou , Hang Su , Dong Yan , Jun Zhu

Conventional wisdom holds that large-batch training is fundamentally incompatible with Reinforcement Learning (RL) - beyond a modest threshold, increasing batch sizes typically yields diminishing returns or performance degradation due to…

Machine Learning · Statistics 2026-05-22 Jongchan Park

In Continual learning (CL) balancing effective adaptation while combating catastrophic forgetting is a central challenge. Many of the recent best-performing methods utilize various forms of prior task data, e.g. a replay buffer, to tackle…

Machine Learning · Computer Science 2023-06-07 Nader Asadi , MohammadReza Davari , Sudhir Mudur , Rahaf Aljundi , Eugene Belilovsky

Offline safe reinforcement learning (OSRL) involves learning a decision-making policy to maximize rewards from a fixed batch of training data to satisfy pre-defined safety constraints. However, adapting to varying safety constraints during…

Machine Learning · Computer Science 2025-05-29 Yassine Chemingui , Aryan Deshwal , Honghao Wei , Alan Fern , Janardhan Rao Doppa

Inspired by the recent successes of Inverse Optimization (IO) across various application domains, we propose a novel offline Reinforcement Learning (ORL) algorithm for continuous state and action spaces, leveraging the convex loss function…

Machine Learning · Computer Science 2026-03-19 Ioannis Dimanidis , Tolga Ok , Peyman Mohajerin Esfahani

Despite the outstanding performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning from continuous data streams in real-world scenarios. Current Non-Exemplar Class-Incremental Learning…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Liang Bai , Hong Song , Yucong Lin , Tianyu Fu , Deqiang Xiao , Danni Ai , Jingfan Fan , Jian Yang

In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach…

Machine Learning · Computer Science 2023-12-15 Zhenrong Liu , Yang Li , Yi Gong , Yik-Chung Wu

Acquiring new knowledge without forgetting what has been learned in a sequence of tasks is the central focus of continual learning (CL). While tasks arrive sequentially, the training data are often prepared and annotated independently,…

Machine Learning · Computer Science 2024-01-31 Thuy-Trang Vu , Shahram Khadivi , Mahsa Ghorbanali , Dinh Phung , Gholamreza Haffari

Class-Incremental Learning (CIL) aims to train a reliable model with the streaming data, which emerges unknown classes sequentially. Different from traditional closed set learning, CIL has two main challenges: 1) Novel class detection. The…

Machine Learning · Computer Science 2020-09-01 Yang Yang , Zhen-Qiang Sun , HengShu Zhu , Yanjie Fu , Hui Xiong , Jian Yang

Reinforcement learning (RL) using foundation models for policy approximations in multi-turn tasks remains challenging. We identify two main limitations related to sparse reward settings and policy gradient updates, based on which we…

Machine Learning · Computer Science 2025-11-14 Georgios Papoudakis , Thomas Coste , Jianye Hao , Jun Wang , Kun Shao

One of the key differences between the learning mechanism of humans and Artificial Neural Networks (ANNs) is the ability of humans to learn one task at a time. ANNs, on the other hand, can only learn multiple tasks simultaneously. Any…

Machine Learning · Computer Science 2019-03-26 Khurram Javed , Faisal Shafait

Current mainstream deep learning techniques exhibit an over-reliance on extensive training data and a lack of adaptability to the dynamic world, marking a considerable disparity from human intelligence. To bridge this gap, Few-Shot…

Artificial Intelligence · Computer Science 2025-04-30 Renye Zhang , Yimin Yin , Jinghua Zhang

Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a…

Machine Learning · Computer Science 2022-11-15 Shengpu Tang , Felipe Vieira Frujeri , Dipendra Misra , Alex Lamb , John Langford , Paul Mineiro , Sebastian Kochman

Offline reinforcement learning (RL) is challenged by the distributional shift between learning policies and datasets. To address this problem, existing works mainly focus on designing sophisticated algorithms to explicitly or implicitly…

Machine Learning · Computer Science 2022-10-18 Yang Yue , Bingyi Kang , Xiao Ma , Zhongwen Xu , Gao Huang , Shuicheng Yan

Continual learning of partially similar tasks poses a challenge for artificial neural networks, as task similarity presents both an opportunity for knowledge transfer and a risk of interference and catastrophic forgetting. However, it…

Machine Learning · Statistics 2024-05-31 Naoki Hiratani

Reinforcement learning (RL) is an area of significant research interest, and safe RL in particular is attracting attention due to its ability to handle safety-driven constraints that are crucial for real-world applications. This work…

Systems and Control · Electrical Eng. & Systems 2023-05-26 Song Bo , Bernard T. Agyeman , Xunyuan Yin , Jinfeng Liu

Online reinforcement learning (RL) excels in complex, safety-critical domains but suffers from sample inefficiency, training instability, and limited interpretability. Data attribution provides a principled way to trace model behavior back…

Machine Learning · Computer Science 2025-10-07 Yuzheng Hu , Fan Wu , Haotian Ye , David Forsyth , James Zou , Nan Jiang , Jiaqi W. Ma , Han Zhao