# Volatility-Clustering Adaptation for Financial Time Series

arXiv: https://arxiv.org/abs/2609.37715 · HTML: https://mlsanity.com/paper/2609.37715/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013)
- [Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks](https://mlsanity.com/paper/1506.03099/) (2015)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution](https://mlsanity.com/paper/2202.10054/) (2022)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [LESS: Selecting Influential Data for Targeted Instruction Tuning](https://mlsanity.com/paper/2402.04333/) (2024)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Soft-DTW: a Differentiable Loss Function for Time-Series](https://mlsanity.com/paper/1703.01541/) (2017)
- [Professor Forcing: A New Algorithm for Training Recurrent Networks](https://mlsanity.com/paper/1610.09038/) (2016)
- [Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting](https://mlsanity.com/paper/2310.08278/) (2023)
- [Quant GANs: Deep Generation of Financial Time Series](https://mlsanity.com/paper/1907.06673/) (2019)
- [Qlib: An AI-oriented Quantitative Investment Platform](https://mlsanity.com/paper/2009.11189/) (2020)
- [Shape and Time Distortion Loss for Training Deep Time Series Forecasting Models](https://mlsanity.com/paper/1909.09020/) (2019)
- [HIST: A Graph-based Framework for Stock Trend Forecasting via Mining Concept-Oriented Shared Information](https://mlsanity.com/paper/2110.13716/) (2021)
- [In-Context Fine-Tuning for Time-Series Foundation Models](https://mlsanity.com/paper/2410.24087/) (2024)
- [MASTER: Market-Guided Stock Transformer for Stock Price Forecasting](https://mlsanity.com/paper/2312.15235/) (2023)
- [Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs](https://mlsanity.com/paper/2405.02774/) (2024)
- [Kronos: A Foundation Model for the Language of Financial Markets](https://mlsanity.com/paper/2508.02739/) (2025)
- [DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting](https://mlsanity.com/paper/2306.09862/) (2023)
- [Low-Rank Adaptation of Time Series Foundational Models for Out-of-Domain Modality Forecasting](https://mlsanity.com/paper/2405.10216/) (2024)
- [Lightweight Online Adaption for Time Series Foundation Model Forecasts](https://mlsanity.com/paper/2502.12920/) (2025)
- [TRACE: Time SeRies PArameter EffiCient FinE-tuning](https://mlsanity.com/paper/2503.16991/) (2025)
- [Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization](https://mlsanity.com/paper/2503.01936/) (2025)

## Abstract (arXiv)

Time-series foundation models are increasingly adapted to new domains through fine-tuning on target data, under the implicit assumption that more target data yields better forecasts. We show that this assumption can fail in financial forecasting, where individual price changes are difficult to predict, but large moves tend to cluster, creating alternating calm and turbulent periods. Using financial foundation models trained on price bars of open, high, low, close, and volume, we argue that adapting to financial domains requires training signals beyond next-token prediction. We introduce Volatility-Clustering Adaptation (VCA), which augments next-token cross-entropy with a differentiable penalty on the autocorrelation of squared returns, the standard statistical signature of volatility clustering. This additional objective provides a multi-step training signal by matching the resulting dependence structure of autoregressive rollouts to those of the realized future. Across three asset sets and two evaluation conventions, VCA improves adaptation over the pre-trained model, with the strongest gains under the primary evaluation (textscfore), driven primarily by reduced variance error. Overall, our results suggest that effective financial adaptation requires objectives that capture domain-specific temporal structure beyond token-level prediction.