# Adaptive Data Augmentation with Multi-armed Bandit: Sample-Efficient Embedding Calibration for Implicit Pattern Recognition

arXiv: https://arxiv.org/abs/2602.19385 · HTML: https://mlsanity.com/paper/2602.19385/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 51 of its 75 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Builds on (most cited first, 30 of 51)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [Diffusion Models: A Comprehensive Survey of Methods and Applications](https://mlsanity.com/paper/2209.00796/) (2022)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- ["Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models](https://mlsanity.com/paper/2308.03825/) (2023)
- [Active Example Selection for In-Context Learning](https://mlsanity.com/paper/2211.04486/) (2022)
- [Head-to-Tail: How Knowledgeable are Large Language Models (LLMs)? A.K.A. Will LLMs Replace Knowledge Graphs?](https://mlsanity.com/paper/2308.10168/) (2023)
- [Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering](https://mlsanity.com/paper/2212.10375/) (2022)
- [What Makes Good Examples for Visual In-Context Learning?](https://mlsanity.com/paper/2301.13670/) (2023)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!](https://mlsanity.com/paper/2303.08559/) (2023)
- [Let's Sample Step by Step: Adaptive-Consistency for Efficient Reasoning and Coding with LLMs](https://mlsanity.com/paper/2305.11860/) (2023)
- [A Survey on LLM-Generated Text Detection: Necessity, Methods, and Future Directions](https://mlsanity.com/paper/2310.14724/) (2023)
- [A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent](https://mlsanity.com/paper/1905.11261/) (2019)
- [Benchmarking large language models for biomedical natural language processing applications and recommendations](https://mlsanity.com/paper/2305.16326/) (2023)
- [The Neglected Tails in Vision-Language Models](https://mlsanity.com/paper/2401.12425/) (2024)
- [Instruction-tuned Language Models are Better Knowledge Learners](https://mlsanity.com/paper/2402.12847/) (2024)
- [Active Learning Principles for In-Context Learning with Large Language Models](https://mlsanity.com/paper/2305.14264/) (2023)
- [How Many Demonstrations Do You Need for In-context Learning?](https://mlsanity.com/paper/2303.08119/) (2023)
- [CoRAL: Collaborative Retrieval-Augmented Large Language Models Improve Long-tail Recommendation](https://mlsanity.com/paper/2403.06447/) (2024)
- [FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning](https://mlsanity.com/paper/2103.13822/) (2021)
- [Implicit Reasoning in Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2509.02350/) (2025)
- [A Survey on Data Synthesis and Augmentation for Large Language Models](https://mlsanity.com/paper/2410.12896/) (2024)
- [RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards](https://mlsanity.com/paper/2410.13509/) (2024)
- [Fed-CBS: A Heterogeneity-Aware Client Sampling Mechanism for Federated Learning via Class-Imbalance Reduction](https://mlsanity.com/paper/2209.15245/) (2022)
- [Data Augmentation using Large Language Models: Data Perspectives, Learning Paradigms and Challenges](https://mlsanity.com/paper/2403.02990/) (2024)
- [Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits](https://mlsanity.com/paper/1507.04523/) (2015)

## Abstract (arXiv)

Recognizing implicit visual and textual patterns is essential in many real-world applications of modern AI. However, tackling long-tail pattern recognition tasks remains challenging for current pre-trained foundation models such as LLMs and VLMs. While finetuning pre-trained models can improve accuracy in recognizing implicit patterns, it is usually infeasible due to a lack of training data and high computational overhead. In this paper, we propose ADAMAB, an efficient embedding calibration framework for few-shot pattern recognition. To maximally reduce the computational costs, ADAMAB trains embedder-agnostic light-weight calibrators on top of fixed embedding models without accessing their parameters. To mitigate the need for large-scale training data, we introduce an adaptive data augmentation strategy based on the Multi-Armed Bandit (MAB) mechanism. With a modified upper confidence bound algorithm, ADAMAB diminishes the gradient shifting and offers theoretically guaranteed convergence in few-shot training. Our multi-modal experiments justify the superior performance of ADAMAB, with up to 40% accuracy improvement when training with less than 5 initial data samples of each class.