Residual Learning

Follow this topic Ask about this topic

Momentum

17 papers in the last four weeks, up 143% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 103

All topics

Hybrid Neural-Classical Correction for Frozen Time Series Foundation Models: A Comprehensive Ablation Study on High-Frequency Stock Prediction
Aug 9, 2026Kasun Dewage, Suranadi De Silva, Shankhadeep MondalResidual Learning Time Series Forecasting
Dept. of Mathematics University of Central Florida Orlando, FL, USA · Dept. of Computer Science University of Central Florida Orlando, FL, USA
SRE-FER: Regional residual evidence learning for mitigating local evidence dilution in fine-grained facial expression recognition
Aug 9, 2026Jiaye Song, Ruochen Zhang, Yuliang Wang +1Residual Learning Facial Expression Recognition
Tiangong University, No. 399 Binshuixi Road, Xiqing District, Tianjin 300387, China
Deep Learning-Based Statistical Downscaling of Sea Surface Temperature Using a Residual Corrective Neural Network
Aug 9, 2026Onkar Jadhav, Tim French, Ivica Janekovic +2Climate Science Residual Learning
School of Earth and Oceans, UWA Oceans Institute, University of Western Australia, Crawley, WA, Australia. · School of Physics, Maths and Computing, Computer Science and Software Engineering, University of Western Australia, Crawley, WA, Australia. · School of Engineering, UWA Oceans Institute, University of Western Australia, Crawley, WA, Australia.
TEMPER: Tensorized Efficient Manifold-constrained Parameterization for Expressive Residual Routing
Aug 8, 2026Yuxuan Gu, Wuyang Zhou, Huijun Xing +1Residual Learning Hyper-Connections
Department of Electrical and Electronic Engineering, Imperial College London
Residual Algebra for Representation-Preserving Learning
Aug 7, 2026Yao WuRepresentation Learning Quantitative Finance
Beyond Residual Connections: Manifold-Constrained Hyper-Connections for Robust Speaker Representation Learning
Aug 6, 2026Zezhong Jin, Xiaoyu Wang, Zhe Li +4Audio Representation Learning Residual Learning
Dept. of EEE, The Hong Kong Polytechnic University · Baidu Inc. · Speech, Language, and Cognition Laboratory, The University of Hong Kong, Hong Kong SAR
When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters
Aug 5, 2026Fangxin Wang, Ziyi Zhang, Diyi Zhuang +4Residual Learning Time Series Forecasting
University of Illinois Chicago · Texas A&M University · Massachusetts Institute of Technology +1
When Proxy Prediction Becomes Equation Reconstruction: Diagnostics and Residual Learning for Factor-Derived Proxy Supervision
Aug 5, 2026Chayan Lahiri, Ahmed Shafee, Cody FehringerDistribution Shift Robustness Residual Learning
Department of Geosciences, Adams State University, Alamosa, Colorado, USA · Department of Computer Science, Adams State University, Alamosa, Colorado, USA · Devils Staircase Wildland Fire Module, Siuslaw National Forest, US Forest Service
HiResNets: Native Full-HD Video Recognition with Foveal Residual Streams
Aug 3, 2026Shivani Mall, Swarnim Jain, Joao F. HenriquesResidual Learning Active Visual Perception
Visual Geometry Group, University of Oxford
Sphere Retraction Normalizations
Aug 2, 2026Jie Zhang, Cheng-Fang Su, Yi-Jui Huang +1Residual Learning Riemannian Geometry
Department of Computer Science and Information Engineering, National Central University, Taiwan · Department of Applied Mathematics, National Yang Ming Chiao Tung University, Taiwan · Department of Mathematics, National Central University, Taiwan
TREA-Net: A Transferable Residual Epidemiological Adaptation Network for Dengue Incidence Forecasting
Jul 29, 2026Inesh Shukla, Madhurima Panja, Tanujit Chakraborty +1Epidemic Forecasting Residual Learning
International Institute of Information Technology Hyderabad, India · SAFIR, Sorbonne University Abu Dhabi, United Arab Emirates · Sorbonne Center for Artificial Intelligence, Sorbonne Universit´e, Paris, France
Attribution and Uncertainty Behavior of Learned Residual Gyro Correction for Gyro-Stellar Estimation
Jul 27, 2026Mariela De Lucas Álvarez, Melvin Laux, Arthur de Freitas Precht +4Residual Learning Aleatoric Uncertainty
Robotics Innovation Center, German Research Center for AI (DFKI GmbH), Bremen, Germany · Airbus Defence and Space GmbH, Immenstaad, Germany
Mechanisms of Width Scaling in Normalized Residual Networks: The Effective Alignment Dimension
Jul 27, 2026Jinhao Zhang, Zeyu Liu, Zicheng Yan +4Neural Network Generalization Residual Learning
Beijing University of Posts and Telecommunications · Institute of Computing Technology, Chinese Academy of Sciences · University of Science and Technology of China +1
Probabilistic Residual Learning for Online Recommendations
Jul 23, 2026Wenyuan Wang, Yusong Zhao, Zihao Xu +11Residual Learning Recommender Systems
Rutgers University · Piscataway, New Jersey, United States · Meta +4
Dynamical and Optimization Trade-offs of Levi--Civita Coordinates for Learned Close-Encounter Dynamics
Jul 22, 2026Abhishek ShankarResidual Learning Hamiltonian Dynamics
Dual Attention Residuals
Jul 21, 2026Xingda Yu, Yining Li, Xinzhang Liu +5Transformer Cross-Attention
TeleAI
Certifying Residual Architectures from Their Primitives: A Sharp Stability Threshold
Jul 16, 2026Hyemin Gu, Michael Tyrrell, Tuhin Sahai +1Neural Network Verification Residual Learning
University of Massachusetts Amherst · SRI International
Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
Jul 15, 2026Katie EverettTransformer FFNs Transformer
MIT CSAIL
DeepLoop: Depth Scaling for Looped Transformers
Jul 15, 2026Shuzhen Li, Yifan Zhang, Jiacheng Guo +2Residual Learning Recurrent Transformers
Princeton University · University of California, Los Angeles
Learning Physics-Guided Residual Dynamics for Deformable Object Simulation
Jul 15, 2026Shivansh Patel, Kaifeng Zhang, Sanjay Pokkali +2Residual Learning Residual Dynamics Learning
UIUC · Columbia University
Learning Residual Kinematic Corrections for Continuous Neural Decoding via Reinforcement Learning
Jul 13, 2026Jiamian Li, Niall McShane, Attila Korik +6Brain-Computer Interfaces Neural Decoding
Department of Computer Science, University of Bath, Bath, BA2 7AY · Intelligent Systems Research Centre, University of Ulster, BT48 7JL · Bath Institute for the Augmented Human, University of Bath, Bath, BA2 7AY +1
Diffusion-Residual Model Predictive Steering Control for Vehicle Stabilization at the Limit of Handling under Model Uncertainty
Jul 11, 2026Bongsob SongResidual Learning Model Predictive Control
Department of Mobility Engineering, Ajou University, Suwon, South Korea
Physics-Informed Machine Learning Under Small-Data Constraints: Lessons from Abrasive Waterjet Milling
Jul 8, 2026Sarah Grewe, Jörg FrochteSurrogate Modeling Residual Learning
Bochum University of Applied Sciences Germany
Wasserstein Residuals: Learning Gradient Flows from Population Dynamics
Jul 6, 2026Markus Heinonen, Yair Shenfeld, Ricardo Baptista +4Dynamical Systems Wasserstein Gradient Flows
Basis Research Institute · Aalto University · Brown University +2
Minimum Block Width for Universal Approximation by Residual Neural Networks with Inner Width One
Jul 6, 2026Qi Zhou, Xuan Zhou, Xiao-Song YangReLU Neural Networks Residual Learning
School of Mathematics and Statistics, Huazhong University of Science and Technology, Wuhan, 430074, Hubei, P.R. China. · Hubei Key Laboratory of Engineering Modeling and Scientific Computing, Huazhong University of Science and Technology, Wuhan, 430074, Hubei, P.R. China.
Interpretation-Oriented Cloud Removal via Observation-Anchored Residual Flow with Geo-Contextual Alignment
Jul 2, 2026Ziyao Wang, Maonan Wang, Yucheng He +5Residual Learning Image Restoration
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Shenzhen, China · Shanghai Ai Lab, Shanghai, China · Faculty of Geosciences and Engineering, Southwest Jiaotong University, Chengdu,2026 China
Review Residuals: Update-Conditioned Residual Gating for Transformers
Jun 30, 2026Kyle KramerTransformer Residual Learning
NeraTech LLC
Black-Box Assisted Regression: Phase Transitions and Minimax Optimality
Jun 24, 2026Yan ZhouResidual Learning Nonparametric Regression
School of Mathematics and Statistics, Changsha University of Science and Technology.
Semantic Allocation in Ordered Bottlenecks: Predictive Residual Inference for Visual Representation Learning
Jun 23, 2026Erik Ayari, Manuel Traub, Martin V. ButzRepresentation Learning Visual Representation Learning
Neuro-Cognitive Modeling Group, University of Tübingen, Tübingen, Germany
Low-Rank Attention Residuals
Jun 19, 2026Jonathan SuLow-Rank Attention Decoder-Only Language Models
Independent Researcher

Aug 9, 2026, cs.LGJ/K move · Enter open · S save

Hybrid Neural-Classical Correction for Frozen Time Series Foundation Models: A Comprehensive Ablation Study on High-Frequency Stock Prediction

Kasun Dewage, Suranadi De Silva, Shankhadeep Mondal

Dept. of Mathematics University of Central Florida Orlando, FL, USA · Dept. of Computer Science University of Central Florida Orlando, FL, USA

Residual Learning Time Series Forecasting Financial Time Series Time-Series Foundation Models

Open paper AskPDF arXiv

Foundation models for time series forecasting demonstrate impressive zero-shot generalization but often underperform on specialized domains such as high-frequency finance. We present a comprehensive study of hybrid neural-classical correction for adapting frozen TimesFM (200M parameters) to stock return prediction during the volatile opening trading hour. We compare two neural correction architectures - AttnCorrect (multi-head self-attention, approximately 471K parameters) and GatedLinear (low-rank bilinear projection with gating, approximately 49K parameters) - each augmented with Random Forest residual learning. Through systematic ablation across 10 major technology stocks (NVDA, MSFT, AAPL, GOOG, GOOGL, AMZN, META, AVGO, TSLA, NFLX) spanning 2 million data points, we reveal critical insights: (1) The hybrid neural-classical approach achieves 0.597 pooled correlation and 6.4x mean per-day correlation improvement over frozen TimesFM; (2) Classical residual learning (Random Forest) provides the largest single-component contribution, matching or exceeding the neural correction component; (3) Simpler neural architectures surprisingly outperform complex ones when classical residual learning is removed; (4) Self-attention provides the largest neural-only contribution. GatedLinear+RF achieves best overall performance with 9x fewer neural parameters than AttnCorrect+RF. We report three complementary correlation metrics - mean per-day, cross-day cumulative, and pooled - to provide a complete picture of predictive quality. Our results provide practical guidance: effective foundation model adaptation requires careful integration of neural and classical components, with classical methods playing a crucial complementary role.

Momentum

Related topics

Latest papers 103