Imagen de Portada

Rethinking Adam for Time Series Forecasting: A Simple Heuristic to Improve Optimization under Distribution Shifts

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Dong, Yuze, Wu, Jinsong
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline
por: Liu, Xvyuan, et al.
Publicado: (2025)

Evolving Multi-Scale Normalization for Time Series Forecasting under Distribution Shifts
por: Qin, Dalin, et al.
Publicado: (2024)

Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift
por: Sun, Yanru, et al.
Publicado: (2024)

APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift
por: Li, Yujie, et al.
Publicado: (2025)

Human in the Loop Adaptive Optimization for Improved Time Series Forecasting
por: Tiomoko, Malik, et al.
Publicado: (2025)

Simple Contrastive Representation Learning for Time Series Forecasting
por: Zheng, Xiaochen, et al.
Publicado: (2023)

Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift
por: Chen, Mouxiang, et al.
Publicado: (2023)

The Forecast After the Forecast: A Post-Processing Shift in Time Series
por: Liang, Daojun, et al.
Publicado: (2026)

Rethinking Post-Training Recipes for Multimodal Time-Series Forecasting
por: Liu, Haoxin, et al.
Publicado: (2026)

Simple Feedfoward Neural Networks are Almost All You Need for Time Series Forecasting
por: Sun, Fan-Keng, et al.
Publicado: (2025)

Causal Time Series Modeling of Supraglacial Lake Evolution in Greenland under Distribution Shift
por: Hossain, Emam, et al.
Publicado: (2025)

AverageTime: Enhance Long-Term Time Series Forecasting with Simple Averaging
por: Zhao, Gaoxiang, et al.
Publicado: (2024)

Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective
por: Wang, Chengsen, et al.
Publicado: (2024)

Bias as a Virtue: Rethinking Generalization under Distribution Shifts
por: Chen, Ruixuan, et al.
Publicado: (2025)

Addressing Concept Shift in Online Time Series Forecasting: Detect-then-Adapt
por: Zhang, YiFan, et al.
Publicado: (2024)

Expectation Consistency Loss: Rethink Confidence Calibration under Covariate Shift
por: Dong, Jinzong, et al.
Publicado: (2026)

ReNF: Rethinking the Design of Neural Long-Term Time Series Forecasters
por: Lu, Yihang, et al.
Publicado: (2025)

DisenTS: Disentangled Channel Evolving Pattern Modeling for Multivariate Time Series Forecasting
por: Liu, Zhiding, et al.
Publicado: (2024)

Minusformer: Improving Time Series Forecasting by Progressively Learning Residuals
por: Liang, Daojun, et al.
Publicado: (2024)

Nonstationary Time Series Forecasting via Unknown Distribution Adaptation
por: Li, Zijian, et al.
Publicado: (2024)

LeapTS: Rethinking Time Series Forecasting as Adaptive Multi-Horizon Scheduling
por: Pan, Sheng, et al.
Publicado: (2026)

Improving Forecasts for Heterogeneous Time Series by "Averaging", with Application to Food Demand Forecast
por: Neubauer, Lukas, et al.
Publicado: (2023)

DeRegiME: Deep Regime Mixtures for Probabilistic Forecasting under Distribution Shift
por: Wood, Kieran, et al.
Publicado: (2026)

TSLANet: Rethinking Transformers for Time Series Representation Learning
por: Eldele, Emadeldeen, et al.
Publicado: (2024)

ForecastGrapher: Redefining Multivariate Time Series Forecasting with Graph Neural Networks
por: Cai, Wanlin, et al.
Publicado: (2024)

Metadata Matters for Time Series: Informative Forecasting with Transformers
por: Dong, Jiaxiang, et al.
Publicado: (2024)

Graphs Generalization under Distribution Shifts
por: Tian, Qin, et al.
Publicado: (2024)

Noise Titration: Exact Distributional Benchmarking for Probabilistic Time Series Forecasting
por: Wang, Qilin
Publicado: (2026)

Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations
por: Grover, Shivam, et al.
Publicado: (2024)

PDETime: Rethinking Long-Term Multivariate Time Series Forecasting from the perspective of partial differential equations
por: Qi, Shiyi, et al.
Publicado: (2024)

Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
por: Zhao, Lifan, et al.
Publicado: (2024)

Three-Stage Learning Unlocks Strong Performance in Simple Models for Long-Term Time Series Forecasting
por: Yu, Zhenan, et al.
Publicado: (2026)

Rethinking Recurrent Neural Networks for Time Series Forecasting: A Reinforced Recurrent Encoder with Prediction-Oriented Proximal Policy Optimization
por: Lai, Xin, et al.
Publicado: (2026)

Revisiting Attention for Multivariate Time Series Forecasting
por: Wu, Haixiang
Publicado: (2024)

S2TX: Cross-Attention Multi-Scale State-Space Transformer for Time Series Forecasting
por: Wu, Zihao, et al.
Publicado: (2025)

AROpt: An Optimization Method for Autoregressive Time Series Forecasting
por: Li, Zheng, et al.
Publicado: (2026)

Fully Automated Correlated Time Series Forecasting in Minutes
por: Wu, Xinle, et al.
Publicado: (2024)

HTMformer: Hybrid Time and Multivariate Transformer for Time Series Forecasting
por: Wang, Tan, et al.
Publicado: (2025)

A Unified Hyperparameter Optimization Pipeline for Transformer-Based Time Series Forecasting Models
por: Xu, Jingjing, et al.
Publicado: (2025)

Rethinking Time Series Forecasting with LLMs via Nearest Neighbor Contrastive Learning
por: Bogahawatte, Jayanie, et al.
Publicado: (2024)