mlsanityData to 7 Oct 2026

Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization

arXiv 2410.07018 ↗First posted 9 Oct 2024cs.LG cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Out-of-Distribution (OOD) generalization in machine learning is a burgeoning area of study. Its primary goal is to enhance the adaptability and resilience of machine learning models when faced with new, unseen, and potentially adversarial data that significantly diverges from their original training datasets. In this paper, we investigate time series OOD generalization via pre-trained Large Language Models (LLMs). We first propose a novel Tri-level learning framework for Time Series OOD generalization, termed TTSO, which considers both sample-level and group-level uncertainties. This formula offers a fresh theoretic perspective for formulating and analyzing OOD generalization problem. In addition, we provide a theoretical analysis to justify this method is well motivated. We then develop a stratified localization algorithm tailored for this tri-level optimization problem, theoretically demonstrating the guaranteed convergence of the proposed algorithm. Our analysis also reveals that the iteration complexity to obtain an ε-stationary point is bounded by O(frac1ε2). Extensive experiments on real-world datasets have been conducted to elucidate the effectiveness of the proposed method.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 47 of its 70 references that are in the map. First posted on arXiv 9 Oct 2024.

Builds on

47 of 70 references.

References · 47

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2021Convex optimizationcited by 2,479
  6. 2019Invariant Risk Minimizationcited by 1,832
  7. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  8. 2018An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modelingcited by 1,447
  9. 2021Robust fine-tuning of zero-shot modelscited by 785
  10. 2021Domain Generalization: A Surveycited by 760
  11. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  12. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
35 more
  1. 2023One Fits All:Power General Time Series Analysis by Pretrained LMcited by 615
  2. 2021Domain Generalization with MixStylecited by 563
  3. 2021TS2Vec: Towards Universal Representation of Time Seriescited by 463
  4. 2021Towards Out-Of-Distribution Generalization: A Surveycited by 431
  5. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  6. 2020Self-Challenging Improves Cross-Domain Generalizationcited by 426
  7. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 293
  8. 2018Explicit Inductive Bias for Transfer Learning with Convolutional Networkscited by 226
  9. 2020Bilevel Optimization: Convergence Analysis and Enhanced Designcited by 219
  10. 2023Large Language Models as General Pattern Machinescited by 196
  11. 2022PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecastingcited by 170
  12. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 170
  13. 2021Pretrained Transformers as Universal Computation Enginescited by 162
  14. 2023Text-to-Audio Generation using Instruction-Tuned LLM and Latent Diffusion Modelcited by 145
  15. 2020An Empirical Study on Robustness to Spurious Correlations using Pre-trained Language Modelscited by 133
  16. 2020Learning explanations that are hard to varycited by 132
  17. 2021AdaRNN: Adaptive Learning and Forecasting of Time Seriescited by 120
  18. 2023Large Language Models are Few-Shot Health Learnerscited by 115
  19. 2023Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Modelscited by 58
  20. 2020A Unified Single-loop Alternating Gradient Projection Algorithm for Nonconvex-Concave and Convex-Nonconcave Minimax Problemscited by 56
  21. 2022Prompt Vision Transformer for Domain Generalizationcited by 52
  22. 2023Enhancing Recommender Systems with Large Language Model Reasoning Graphscited by 52
  23. 2022Leveraging Language Foundation Models for Human Mobility Forecastingcited by 50
  24. 2020Unadversarial Examples: Designing Objects for Robust Visioncited by 45
  25. 2023Leveraging Large Language Models for Pre-trained Recommender Systemscited by 42
  26. 2018Robust Optimization over Multiple Domainscited by 34
  27. 2022Domain-invariant Feature Exploration for Domain Generalizationcited by 34
  28. 2022Out-of-Distribution Representation Learning for Time Series Classificationcited by 30
  29. 2022Distributed Distributionally Robust Optimization with Non-Convex Objectivescited by 14
  30. 2022Asynchronous Distributed Bilevel Optimizationcited by 13
  31. 2023ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representationscited by 10
  32. 2021Robust Domain-Free Domain Generalization with Class-aware Alignmentcited by 6
  33. 2023Provably Convergent Federated Trilevel Learningcited by 6
  34. 2023FedAL: Black-Box Federated Knowledge Distillation Enabled by Adversarial Learningcited by 5
  35. 2013A Polyhedral Approximation Framework for Convex and Robust Distributed Optimizationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 3.

12 papers.

  1. 2025PR-Attack: Coordinated Prompt-RAG Attacks on Retrieval-Augmented Generation in Large Language Models via Bilevel Optimizationcited by 29
  2. 2024Embracing Large Language Models in Traffic Flow Forecastingcited by 3
  3. 2025HAROOD: A Benchmark for Out-of-distribution Generalization in Sensor-based Human Activity Recognitioncited by 3
  4. 2025Theoretical Foundation of Flow-Based Time Series Generation: Provable Approximation, Generalization, and Efficiencycited by 2
  5. 2025Stable Preference Optimization: A Bilevel Approach to Catastrophic Preference Shiftcited by 1
  6. 2025UrbanMind: Towards Urban General Intelligence via Tool-Enhanced Retrieval-Augmented Generation and Multilevel Optimizationcited by 0
  7. 2025Synergistic Localization and Sensing in MIMO-OFDM Systems via Mixed-Integer Bilevel Learningcited by 0
  8. 2025ERIS: An Energy-Guided Feature Disentanglement Framework for Out-of-Distribution Time Series Classificationcited by 0
  9. 2025ViTs: Teaching Machines to See Time Series Anomalies Like Human Expertscited by 0
  10. 2026LLM-Driven Multi-Turn Task-Oriented Dialogue Synthesis for Realistic Reasoningcited by 0
  11. 2026TableNet A Large-Scale Table Dataset with LLM-Powered Autonomouscited by 0
  12. 2026First-order Constrained Trilevel Optimization Over Distributed Networks for Robust Coreset Selectioncited by 0