paper-with-me

Papers

FreqLite: A Lightweight Frequency-Decomposed Linear Model with Adaptive Reversible Normalization for Robust Long-Term Time-Series Forecasting

2026-05-31 · Mirza Samad Ahmed Baig, Syeda Anshrah Gillani arxiv

Long-term time-series forecasting needs models that are accurate yet efficient enough for commodity hardware. Lightweight linear forecasters are remarkably strong in this regime, yet they leave two openings: reversible instance normalization (RevIN) de-normalizes the entire horizon with a single lookback statistic, which is inaccurate under non-stationarity, and time-domain trend/seasonal decomposition relies on a fixed, non-adaptive filter. We present FreqLite, an ultra-lightweight, channel-independent frequency-decomposed linear forecaster: a learnable, lossless, partition-of-unity spectral filter splits the input into bands that are forecast by per-band linear heads and, unlike low-pass-truncation approaches, the high-frequency band is retained and modeled. FreqLite is the best lightweight model on the standard long-term forecasting benchmarks and, at long lookback (L=336), attains a lower average error than a PatchTST Transformer (0.3244 vs. 0.3587 MSE) while using 4x fewer parameters, 2.2x less memory, and 2.2x less time per epoch on a single 4 GB laptop GPU; although modest in magnitude, its improvements are statistically significant under paired Wilcoxon tests across all matched cells (p < 1e-5). We further introduce Adaptive Reversible Instance Normalization (A-RevIN), a regime-adaptive reversible normalization that strictly generalizes RevIN (recovered exactly when its gate is closed), engages under non-stationarity, and reduces to RevIN without harm on stationary data. We validate this on both a real strongly non-stationary dataset (ILI, up to ~5% MSE reduction) and a controlled synthetic drift sweep in which A-RevIN's benefit and its learned gate both rise monotonically with injected non-stationarity. Every component is independently ablatable (Linear and RLinear are special cases of FreqLite), and all results are reproducible on commodity hardware.

📄 PDF Abstract BibTeX arXiv:2606.01339

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Direct Signal Separation Via Extraction of Local Frequencies with Adaptive Time-Varying Parameters

2020-10-05 · Lin Li, Charles K. Chui, Qingtang Jiang

Real-world phenomena that can be formulated as signals are often affected by a number of factors and appear as multi-component modes. To understand and process such phenomena, "divide-and-conquer" is probably the most co…

Time Series Analysis

ROSE: Register Assisted General Time Series Forecasting with Decomposed Frequency Learning

2024-05-24 · Yihang Wang, Yuying Qiu, Peng Chen, Kai Zhao 외

With the increasing collection of time series data from various domains, there arises a strong demand for general time series forecasting models pre-trained on a large number of time-series datasets to support a variety …

Time SeriesTime Series Forecasting

Head-Free Lightweight Semantic Segmentation with Linear Transformer

2023-01-11 · Bo Dong, Pichao Wang, Fan Wang

Existing semantic segmentation works have been mainly focused on designing effective decoders; however, the computational load introduced by the overall structure has long been ignored, which hinders their applications o…

DecoderSegmentationSemantic Segmentation

FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution

2025-12-01 · Seungho Choi, Jeahun Sung, Jihyong Oh arxiv

Real-image super-resolution (Real-ISR) seeks to recover HR images from LR inputs with mixed, unknown degradations. While diffusion models surpass GANs in perceptual quality, they under-reconstruct high-frequency (HF) det…

Image Super-Resolution

Temporal-adaptive Hierarchical Reinforcement Learning

2020-02-06 · Wen-Ji Zhou, Yang Yu

Hierarchical reinforcement learning (HRL) helps address large-scale and sparse reward issues in reinforcement learning. In HRL, the policy model has an inner representation structured in levels. With this structure, the …

Atari GamesHierarchical Reinforcement LearningMuJoCoreinforcement-learning+2