# Decision-Focused Fine-Tuning of Time Series Foundation Models for Dispatchable Feeder Optimization

arXiv: https://arxiv.org/abs/2503.01936 · HTML: https://mlsanity.com/paper/2503.01936/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 3 Mar 2025.

## Builds on (most cited first, 24 of 24)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Mixed Precision Training](https://mlsanity.com/paper/1710.03740/) (2017)
- [Chronos: Learning the Language of Time Series](https://mlsanity.com/paper/2403.07815/) (2024)
- [A decoder-only foundation model for time-series forecasting](https://mlsanity.com/paper/2310.10688/) (2023)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [Unified Training of Universal Time Series Forecasting Transformers](https://mlsanity.com/paper/2402.02592/) (2024)
- [MOMENT: A Family of Open Time-series Foundation Models](https://mlsanity.com/paper/2402.03885/) (2024)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT](https://mlsanity.com/paper/2302.09419/) (2023)
- [Smart "Predict, then Optimize"](https://mlsanity.com/paper/1710.08005/) (2017)
- [Foundation Models for Time Series Analysis: A Tutorial and Survey](https://mlsanity.com/paper/2403.14735/) (2024)
- [Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment](https://mlsanity.com/paper/2312.12148/) (2023)
- [Decision-Focused Learning: Foundations, State of the Art, Benchmark and Future Opportunities](https://mlsanity.com/paper/2307.13565/) (2023)
- [Foundational Models Defining a New Era in Vision: A Survey and Outlook](https://mlsanity.com/paper/2307.13721/) (2023)
- [Leaving the Nest: Going Beyond Local Loss Functions for Predict-Then-Optimize](https://mlsanity.com/paper/2305.16830/) (2023)
- [Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information](https://mlsanity.com/paper/2307.08964/) (2023)
- [Decision-Aware Learning for Optimizing Health Supply Chains](https://mlsanity.com/paper/2211.08507/) (2022)
- [Benchmarking Time Series Foundation Models for Short-Term Household Electricity Load Forecasting](https://mlsanity.com/paper/2410.09487/) (2024)
- [TaskMet: Task-Driven Metric Learning for Model Learning](https://mlsanity.com/paper/2312.05250/) (2023)
- [Cost-Oriented Load Forecasting](https://mlsanity.com/paper/2107.01861/) (2021)
- [TimeGPT in Load Forecasting: A Large Time Series Model Perspective](https://mlsanity.com/paper/2404.04885/) (2024)
- [A Note on Task-Aware Loss via Reweighing Prediction Loss by Decision-Regret](https://mlsanity.com/paper/2211.05116/) (2022)
- [Achieving the Dispatchability of Distribution Feeders through Prosumers Data Driven Forecasting and Model Predictive Control of Electrochemical Storage](https://mlsanity.com/paper/1602.02265/) (2016)
- [Storage Scheduling with Stochastic Uncertainties: Feasibility and Cost of Imbalances](https://mlsanity.com/paper/1805.02525/) (2018)

## Built on by (most cited first, 5 of 5)

- [TS-Memory: Plug-and-Play Memory for Time Series Foundation Models](https://mlsanity.com/paper/2602.11550/) (2026)
- [Post-Training in Time Series Foundation Models: A Unifying Framework](https://mlsanity.com/paper/2607.20002/) (2026)
- [CENTILE: A Telemetry Foundation Model Evaluated by the Decisions It Drives](https://mlsanity.com/paper/2608.01725/) (2026)
- [Time Series Foundation Models for Process Model Forecasting](https://mlsanity.com/paper/2512.07624/) (2025)
- [Volatility-Clustering Adaptation for Financial Time Series](https://mlsanity.com/paper/2609.37715/) (2026)

## Abstract (arXiv)

Time series foundation models provide a universal solution for generating forecasts to support optimization problems in energy systems. Those foundation models are typically trained in a prediction-focused manner to maximize forecast quality. In contrast, decision-focused learning directly improves the resulting value of the forecast in downstream optimization rather than merely maximizing forecasting quality. The practical integration of forecast values into forecasting models is challenging, particularly when addressing complex applications with diverse instances, such as buildings. This becomes even more complicated when instances possess specific characteristics that require instance-specific, tailored predictions to increase the forecast value. To tackle this challenge, we use decision-focused fine-tuning within time series foundation models to offer a scalable and efficient solution for decision-focused learning applied to the dispatchable feeder optimization problem. To obtain more robust predictions for scarce building data, we use Moirai as a state-of-the-art foundation model, which offers robust and generalized results with few-shot parameter-efficient fine-tuning. Comparing the decision-focused fine-tuned Moirai with a state-of-the-art classical prediction-focused fine-tuning Morai, we observe an improvement of 9.45% in average total daily costs.