English
Related papers

Related papers: Immediate Derivatives Suffice for Online Recurrent…

200 papers

Real-time recurrent learning (RTRL) computes exact online gradients by propagating a Jacobian tensor forward through recurrent dynamics, but at O(n^4) cost per step. Prior work has sought structured approximations (rank-1 compression,…

Machine Learning · Computer Science 2026-03-30 Aur Shalev Merin

We prove local convergence of several notable gradient descent algorithms used in machine learning, for which standard stochastic gradient descent theory does not apply directly. This includes, first, online algorithms for recurrent models…

Dynamical Systems · Mathematics 2021-01-11 Pierre-Yves Massé , Yann Ollivier

The goal of a learner, in standard online learning, is to have the cumulative loss not much larger compared with the best-performing function from some fixed class. Numerous algorithms were shown to have this gap arbitrarily close to zero,…

Machine Learning · Computer Science 2013-03-04 Nina Vaits , Edward Moroshko , Koby Crammer

Recent progress in Large Language Model (LLM) reasoning is increasingly driven by the refinement of post-training loss functions and alignment strategies. However, standard Reinforcement Learning (RL) paradigms like Group Relative Policy…

Machine Learning · Computer Science 2026-01-28 Kishan Panaganti , Zhenwen Liang , Wenhao Yu , Haitao Mi , Dong Yu

Recurrent neural networks (RNNs) are commonly trained with the truncated backpropagation-through-time (TBPTT) algorithm. For the purposes of computational tractability, the TBPTT algorithm truncates the chain rule and calculates the…

Machine Learning · Computer Science 2025-01-15 Samuel Chun-Hei Lam , Justin Sirignano , Konstantinos Spiliopoulos

Offline reinforcement learning (RL) can fail spectacularly when bootstrapped temporal-difference (TD) updates amplify their own errors, driving the critic toward extreme and unusable Q-values. A key counterintuitive insight of this work is…

Machine Learning · Computer Science 2026-05-05 Nan Qiao , Sheng Yue , Shuning Wang , Ju Ren

Reaction-diffusion (RD) equations underpin pattern formation across chemistry, biology, and physics, yet learning stable operators that forecast their long-term dynamics from data remains challenging. Neural-operator surrogates provide…

Machine Learning · Computer Science 2026-02-11 Huseyin Tunc

Retrieval-augmented models couple parametric predictors with non-parametric memories, but their use in streaming supervised learning with concept drift is not well understood. We study online classification in non-stationary environments…

Machine Learning · Computer Science 2025-12-03 Wenzhang Du

Training autonomous agents with sparse rewards is a long-standing problem in online reinforcement learning (RL), due to low data efficiency. Prior work overcomes this challenge by extracting useful knowledge from offline data, often…

Machine Learning · Computer Science 2024-06-07 Qianlan Yang , Yu-Xiong Wang

With the excellent representation capabilities of Pre-Trained Models (PTMs), remarkable progress has been made in non-rehearsal Class-Incremental Learning (CIL) research. However, it remains an extremely challenging task due to three…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Jiawei Zhan , Jun Liu , Jinlong Peng , Xiaochen Chen , Bin-Bin Gao , Yong Liu , Chengjie Wang

Real-time recurrent learning (RTRL) for sequence-processing recurrent neural networks (RNNs) offers certain conceptual advantages over backpropagation through time (BPTT). RTRL requires neither caching past activations nor truncating…

Machine Learning · Computer Science 2024-02-29 Kazuki Irie , Anand Gopalakrishnan , Jürgen Schmidhuber

We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online distributionally robust Markov decision processes (DRMDPs),…

Machine Learning · Computer Science 2024-02-26 Zhishuai Liu , Pan Xu

Offline-to-online reinforcement learning (O2O RL) faces a central challenge between retaining offline conservatism and adapting to online feedback under distribution shift. This challenge arises because data behavior evolves during…

Machine Learning · Computer Science 2026-05-19 Lipeng Zu , Yu Qian , Shayok Chakraborty , Xiaonan Zhang

We study the decentralized online regularized linear regression algorithm over random time-varying graphs. At each time step, every node runs an online estimation algorithm consisting of an innovation term processing its own new…

Machine Learning · Computer Science 2025-10-02 Xiwei Zhang , Tao Li , Xiaozheng Fu

The ResNet architecture has been widely adopted in deep learning due to its significant boost to performance through the use of simple skip connections, yet the underlying mechanisms leading to its success remain largely unknown. In this…

Machine Learning · Computer Science 2024-01-18 Jianing Li , Vardan Papyan

Current methods for training recurrent neural networks are based on backpropagation through time, which requires storing a complete history of network states, and prohibits updating the weights `online' (after every timestep). Real Time…

Machine Learning · Computer Science 2020-06-15 Jacob Menick , Erich Elsen , Utku Evci , Simon Osindero , Karen Simonyan , Alex Graves

Recurrent networks are typically trained with backpropagation through time (BPTT). However, BPTT requires storing the history of all states in the network and then replaying them sequentially backwards in time. This computation appears…

Machine Learning · Computer Science 2026-01-01 Beren Millidge

Decentralized nonconvex optimization has received increasing attention in recent years in machine learning due to its advantages in system robustness, data privacy, and implementation simplicity. However, three fundamental challenges in…

Machine Learning · Computer Science 2021-05-20 Xin Zhang , Jia Liu , Zhengyuan Zhu , Elizabeth S. Bentley

Backpropagation through time (BPTT) is the standard algorithm for training recurrent neural networks (RNNs), which requires separate simulation phases for the forward and backward passes for inference and learning, respectively. Moreover,…

Machine Learning · Computer Science 2023-03-13 Anand Subramoney

Gaussian Graphical Models (GGMs) are widely used to infer conditional dependence structures in high-dimensional data. However, standard precision matrix estimators are highly sensitive to data contamination, such as extreme outliers and…

Applications · Statistics 2026-03-25 Canruo Shen , Xintong Ji , Qiong Li , Wenzhi Yang , Xiaoping Shi
‹ Prev 1 2 3 10 Next ›