AI Paper Atlas

Research map / Time series / Long-term forecasting

Paloma: Phase-Conditioned Residual Modulation for Time Series Forecasting

Jingru Fei, Kun Yi, Wei Fan, Qi Zhang, Zhendong Niu

NeurIPS 2026 · Time series › Long-term forecasting · approach: Attention for time series forecasting · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Paloma, which models phase-dependent structure left in time-series residuals after removing the periodic component, for time series forecasting.

Problem

Explicit periodicity modeling in time series forecasting treats the residual after removing the periodic component as unstructured noise, though the residuals may still carry structured phase-dependent deviations.

Approach

Shows that post-periodic residuals retain phase-dependent deviations and conditions residual modulation on the phase, rather than treating residuals as white noise.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Phase Rotation module (ablation)Paloma · ETTm1, ETTh1, Electricity, Weather, Traffic, Solar-EnergyMSE: ETTm1 0.368 -> 0.363; Traffic 0.471 -> 0.461Improved
add Amplitude Scaling module (ablation)Paloma · ETTm1, ETTh1, Electricity, Weather, Traffic, Solar-EnergyMSE: ETTm1 0.369 -> 0.363; Solar-Energy 0.201 -> 0.197Improved
add both PR and AS modules to the base cycle-residual backbone (ablation)Paloma · ETTm1MSE: 0.376 -> 0.363Improved
add both PR and AS modules on ETTh1 (ablation)Paloma · ETTh1MSE: w/o PR,AS 0.428 vs w/o PR 0.427, w/o AS 0.430; full 0.421Mixed
plug Paloma technique into DLinearDLinear · PEMS03 (avg)MSE: 0.265 -> 0.099Improved
plug Paloma technique into iTransformeriTransformer · PEMS04 (avg)MSE: 0.121 -> 0.092Improved
plug Paloma technique into PatchTSTPatchTST · Electricity (avg)MSE: 0.191 -> 0.172Improved
plug Paloma technique into FilterNetFilterNet · PEMS04 (avg)MSE: 0.146 -> 0.113Improved
use channel-independent Paloma on Traffic with many channelsPaloma · TrafficMSE: Paloma 0.461 vs iTransformer 0.428Hurt
assume a cycle length misaligned with the true period (ablation)Paloma · sensitivity analysisforecast errorHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Surprising findings

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy