3 citations · 4 across the 3 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
EPOC: Endpoint-Preserving Online Correction With Compressed Residual State for Multi-Horizon Time Series Forecasting
Takumi Fujimoto, Hiroaki Nishi
Completed forecasts provide residual feedback, but retaining full residual blocks increases auxiliary state. We propose Endpoint-Preserving Online Correction (EPOC) with a compress…
cs.LG2026
When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting
Takumi Fujimoto, Hiroaki Nishi
Online adaptation can help edge time-series forecasting under distribution drift, but its measured benefit is sensitive to evaluation choices. We study six public multivariate stre…
cs.LG2025★ 1 cited
eagle: early approximated gradient based learning rate estimator
Takumi Fujimoto, Hiroaki Nishi
We propose EAGLE update rule, a novel optimization method that accelerates loss convergence during the early stages of training by leveraging both current and previous step paramet…