arXiv AI
Big Models, Small Gains: Frozen Forecasters as Classifiers on MONSTER
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Oct 2
When, Not How Much: Evaluating Time-Series Foundation Models on Sparse Events
arXiv:2609.39386v1 Announce Type: new Abstract: Pretrained time-series foundation models (TSFMs) are evaluated as forecasters of future values, yet for sparse series many decisions depend only on whi...
arXiv Machine Learning
Oct 23
Random Initialization as a Baseline for Time Series Foundation Models
The study evaluates how much self‑supervised pretraining contributes to time series foundation models (TSFMs) by comparing seven publicly released TSFMs with architecture‑matched randomly initialized versions on the UEA multivariate time series classification archive. Across 183 dataset‑level comparisons, pretraining yields modest accuracy gains (1.43–5.19 percentage points, average 2.58 points), with only one model (NuTime) remaining significant after Holm correction. The results highlight that strong non‑pretrained baselines such as ROCKET, Hydra, and Quant can compete without large‑scale pretraining, underscoring the need to separate architectural effects from pretrained weights in MTSC evaluations.
arXiv Machine Learning
Jul 7
When Do Foundation Models Pay Off? A Break-Even Analysis of Pretrained Time Series Forecasters
arXiv:2607. 04919v1 Announce Type: new Abstract: Deploying a time series foundation model requires GPU infrastructure, engineering overhead, and carries no guarantee of improvement over XGBoost.
arXiv Machine Learning
Oct 7
Retrieval Is Not Enough: Refreshing Memory for Frozen Time-Series Forecasters
arXiv:2610.07834v1 Announce Type: new Abstract: Retrieval-augmented time-series forecasting uses the continuations of historical segments similar to the current context as references for a forecaster...
arXiv Machine Learning
Jun 2
Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification
arXiv:2602. 16224v2 Announce Type: replace Abstract: Time series data are prone to noise in various domains, and training samples may contain low-predictability patterns that deviate from the normal data distribution, leading to training instability or convergence to poor local minima.
arXiv Machine Learning
Jul 2
LeNEPA: No-Augmentation Next-Latent Prediction for Time-Series Representation Learning
arXiv:2607. 00958v1 Announce Type: new Abstract: Time series are central to modern data mining applications, from industrial telemetry and server metrics to finance and physiology, yet time-series self-supervised learning often depends on view and augmentation choices that encode domain-specific invariances.