arXiv Machine Learning
Sep 18
When Does Retrieval Help Time-Series Forecasting?
arXiv:2609. 20193v1 Announce Type: new Abstract: Retrieval plug-ins supply a deep forecaster with information its lookback window cannot carry.
A Later Test Set Is Not a New Domain: Pretraining Familiarity Survives a Contamination-Free Hold-Out
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 12
On the Encoding of Calendar Features in Covariate-Informed Time Series Foundation Models
The paper investigates how different calendar feature encodings influence the performance of covariate-informed time series foundation models (TSFMs). Seven encoding schemes—three target‑agnostic (ordinal, one‑hot, cyclic) and four target‑based—are systematically compared across four state‑of‑the‑art TSFMs on nine datasets that reflect social activity patterns such as weekends and holidays. Results show that encoding choice can change forecast accuracy by up to 9.9 % on non‑holidays and 83 % on holidays, with improvements mainly around holidays and varying effects across models.
arXiv Machine Learning
Jul 15
When Directional Accuracy Lies: A Base-Rate-Honest Benchmark for LoRA-Adapted TimesFM on Equity Forecasting
arXiv:2607. 12248v1 Announce Type: cross Abstract: Large pretrained time-series models such as TimesFM are attractive for financial forecasting, but raw directional accuracy is a misleading scoreboard in equity markets.
arXiv Machine Learning
Jun 26
How Good Can Linear Models Be for Time-Series Forecasting?
arXiv:2606. 27282v1 Announce Type: new Abstract: Time-series forecasting research has been moving steadily toward larger architectures, from specialized transformers to general-purpose foundation models, on the assumption that capacity is what unlocks accuracy.
arXiv Machine Learning
Jun 10
Streaming Knowledge Compilation: Proactive Materiality-Scored Pinning for Time-Evolving LLM Wikis
arXiv:2606. 09877v1 Announce Type: new Abstract: LLM wiki systems compile knowledge into pre-filled KV caches for efficient inference, but assume a static corpus -- an assumption that fails whenever the underlying information landscape evolves.
arXiv Machine Learning
Sep 22
$t_0$: A Time-Series Foundation Model for Forecasting with Context
arXiv:2609.24559v1 Announce Type: new Abstract: We present $t_0$, a family of open-weights foundation models for forecasting with multivariate context. We release its first two members: $\texttt{t0-a...
arXiv AI
Jun 30
MACROCAST: A Vintage-Consistent Time Series Foundation Model for Real-Time Macroeconomic Forecasting
arXiv:2606. 28670v1 Announce Type: cross Abstract: We introduce MACROCAST, a lightweight Time Series Foundation Model (TSFM) for real-time macroeconomic forecasting.
arXiv AI
2d ago
Big Models, Small Gains: Frozen Forecasters as Classifiers on MONSTER
The paper benchmarks two frozen forecasting models, Reverso and Chronos‑Bolt, as feature extractors for time‑series classification on the MONSTER dataset. Using 1%, 10%, and 100% of training labels, the authors compare the models’ frozen representations to four established classifiers and to random‑weight versions of the same models. Results show that pretraining yields higher accuracy than random weights on five of six datasets, but the frozen representations never outperform the best non‑pretrained baseline, performing worse in 15 of 17 settings and tying only twice.
arXiv Machine Learning
Oct 5
On Unlearning for Time-series Forecasting
The paper introduces RDTU, a Residual Diffusion framework designed to enable efficient unlearning in time‑series forecasting models. RDTU first generates a deletion‑compatible base forecast using a retained‑set neural tangent kernel predictor, then assesses the structural support of affected windows via volume contribution metrics, and finally applies a diffusion model to produce residual corrections that approximate counterfactual forecasts. These pseudo‑labels guide a lightweight update, resulting in models that closely match those obtained by exact retraining after data deletion.
Hugging Face Trending Papers
Oct 20
Training-Free Continual Learning for Multimodal Forecasting via Prompt Evolution
Adapting a forecasting system to a changing world classically means retraining. We ask whether the task of continually learning regimes for time series forecasting can be represented by a piece of tex...
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...