QUALS: Corpus Equilibrium for Universal Forecasting via Pattern Quantization and Learnability Synchronization
cs.LG, cs.AI
Submitted: 2026-09-17
Updated: 2026-09-20
Code: https://github.com/blisky-li/QUALS
License: http://creativecommons.org/licenses/by/4.0/
The gist: Ubiquitous time series data across diverse domains enables critical applications in areas such as transportation systems and power grids.
Terminology
Abstract
Ubiquitous time series data across diverse domains enables critical applications in areas such as transportation systems and power grids. Recently, training foundation models on massive datasets to achieve accurate zero-shot forecasting has emerged as a major research focus. However, current studies predominantly prioritize architectural innovations while insufficiently addressing data diversity, often relying on simple data sampling strategies that fail to manage complex data distributions effectively, leading to inefficient use of training data and suboptimal performance. To address this, we propose QUALS, a large-scale time series corpus equilibrium framework. QUALS significantly enhances data efficiency, i.e., enabling existing models to achieve superior performance using only a small fraction of the original training data. Specifically, QUALS operates through two core mechanisms. First, a pattern quantization framework systematically decodes heterogeneous patterns from mixed corpora via vector quantization and uniform binning. Second, a learnability synchronization framework calibrates sampling weights for heterogeneous patterns, bridging the optimization gap between simple and complex motifs to maximize overall training efficiency. Extensive benchmarks demonstrate that pre-training on QUALS consistently achieves superior zero-shot performance, even under substantially reduced training budgets.
Sources
- APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift
- Moirai 2.0: When Less Is More for Time Series Forecasting
- Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Experts
- Timer-XL: Long-Context Transformers for Unified Time Series Forecasting
- GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
- Chronos-2: From Univariate to Universal Forecasting
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- Jukebox: A Generative Model for Music
- Reward Shaping to Mitigate Reward Hacking in RLHF
- Selective Learning for Deep Time Series Forecasting
- TimeGPT-1
- fev-bench: A Realistic Benchmark for Time Series Forecasting
- Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts
- Xihe: Scalable Zero-Shot Time Series Learner Via Hierarchical Interleaved Block Attention
- ARIES: Relation Assessment and Model Recommendation for Deep Time Series Forecasting
- Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks