# In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness

arXiv: https://arxiv.org/abs/2402.11639 · HTML: https://mlsanity.com/paper/2402.11639/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 62 references that are in the map.
- First posted on arXiv 18 Feb 2024.

## Builds on (most cited first, 30 of 35)

- [LaMDA: Language Models for Dialog Applications](https://mlsanity.com/paper/2201.08239/) (2022)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [In-context Learning and Induction Heads](https://mlsanity.com/paper/2209.11895/) (2022)
- [An Explanation of In-context Learning as Implicit Bayesian Inference](https://mlsanity.com/paper/2111.02080/) (2021)
- [What learning algorithm is in-context learning? Investigations with linear models](https://mlsanity.com/paper/2211.15661/) (2022)
- [Are Transformers universal approximators of sequence-to-sequence functions?](https://mlsanity.com/paper/1912.10077/) (2019)
- [Trained Transformers Learn Linear Models In-Context](https://mlsanity.com/paper/2306.09927/) (2023)
- [Transformers Learn Shortcuts to Automata](https://mlsanity.com/paper/2210.10749/) (2022)
- [Looped Transformers as Programmable Computers](https://mlsanity.com/paper/2301.13196/) (2023)
- [Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel](https://mlsanity.com/paper/1908.11775/) (2019)
- [Why Can GPT Learn In-Context? Language Models Implicitly Perform Gradient Descent as Meta-Optimizers](https://mlsanity.com/paper/2212.10559/) (2022)
- [One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention](https://mlsanity.com/paper/2307.03576/) (2023)
- [Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning](https://mlsanity.com/paper/2301.11916/) (2023)
- [Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression](https://mlsanity.com/paper/2306.15063/) (2023)
- [Representational Strengths and Limitations of Transformers](https://mlsanity.com/paper/2306.02896/) (2023)
- [In-Context Convergence of Transformers](https://mlsanity.com/paper/2310.05249/) (2023)
- [Uncovering mesa-optimization algorithms in Transformers](https://mlsanity.com/paper/2309.05858/) (2023)
- [How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?](https://mlsanity.com/paper/2310.08391/) (2023)
- [How Do Transformers Learn Topic Structure: Towards a Mechanistic Understanding](https://mlsanity.com/paper/2303.04245/) (2023)
- [Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining](https://mlsanity.com/paper/2310.08566/) (2023)
- [A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity](https://mlsanity.com/paper/2302.06015/) (2023)
- [How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations](https://mlsanity.com/paper/2310.10616/) (2023)
- [Transformers as Support Vector Machines](https://mlsanity.com/paper/2308.16898/) (2023)
- [Transformers Implement Functional Gradient Descent to Learn Non-Linear Functions In Context](https://mlsanity.com/paper/2312.06528/) (2023)
- [JoMA: Demystifying Multilayer Transformers via JOint Dynamics of MLP and Attention](https://mlsanity.com/paper/2310.00535/) (2023)
- [A Theoretical Analysis on Feature Learning in Neural Networks: Emergence from Inputs and Advantage over Fixed Features](https://mlsanity.com/paper/2206.01717/) (2022)
- [Transformers Learn to Achieve Second-Order Convergence Rates for In-Context Linear Regression](https://mlsanity.com/paper/2310.17086/) (2023)
- [On the Expressive Power of Self-Attention Matrices](https://mlsanity.com/paper/2106.03764/) (2021)
- [What can a Single Attention Layer Learn? A Study Through the Random Features Lens](https://mlsanity.com/paper/2307.11353/) (2023)
- [Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation](https://mlsanity.com/paper/2305.19798/) (2023)

## Built on by (most cited first, 22 of 22)

- [Mechanics of Next Token Prediction with Self-Attention](https://mlsanity.com/paper/2403.08081/) (2024)
- [Fine-grained Analysis of In-context Linear Estimation: Data, Architecture, and Beyond](https://mlsanity.com/paper/2407.10005/) (2024)
- [Can In-context Learning Really Generalize to Out-of-distribution Tasks?](https://mlsanity.com/paper/2410.09695/) (2024)
- [Exploring the Frontiers of Softmax: Provable Optimization, Applications in Diffusion Model, and Beyond](https://mlsanity.com/paper/2405.03251/) (2024)
- [Gating is Weighting: Understanding Gated Linear Attention through In-context Learning](https://mlsanity.com/paper/2504.04308/) (2025)
- [From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics](https://mlsanity.com/paper/2510.06954/) (2025)
- [Optimizing Attention with Mirror Descent: Generalized Max-Margin Token Selection](https://mlsanity.com/paper/2410.14581/) (2024)
- [Transformer learns the cross-task prior and regularization for in-context learning](https://mlsanity.com/paper/2505.12138/) (2025)
- [On the Power of Convolution Augmented Transformer](https://mlsanity.com/paper/2407.05591/) (2024)
- [Context-Scaling versus Task-Scaling in In-Context Learning](https://mlsanity.com/paper/2410.12783/) (2024)
- [When and How Unlabeled Data Provably Improve In-Context Learning](https://mlsanity.com/paper/2506.15329/) (2025)
- [On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective](https://mlsanity.com/paper/2507.23632/) (2025)
- [In-Context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-Separation](https://mlsanity.com/paper/2502.08136/) (2025)
- [Provable In-Context Learning of Nonlinear Regression with Transformers](https://mlsanity.com/paper/2507.20443/) (2025)
- [Softmax ≥ Linear: Transformers may learn to classify in-context by kernel gradient descent](https://mlsanity.com/paper/2510.10425/) (2025)
- [From Unstructured Data to In-Context Learning: Exploring What Tasks Can Be Learned and When](https://mlsanity.com/paper/2406.00131/) (2024)
- [Affine-Scaled Attention: Towards Flexible and Stable Transformer Attention](https://mlsanity.com/paper/2602.23057/) (2026)
- [StaICC: Standardized Evaluation for Classification Task in In-context Learning](https://mlsanity.com/paper/2501.15708/) (2025)
- [Bounds of Chain-of-Thought Robustness: Reasoning Steps, Embed Norms, and Beyond](https://mlsanity.com/paper/2509.21284/) (2025)
- [Review of Hallucination Understanding in Large Language and Vision Models](https://mlsanity.com/paper/2510.00034/) (2025)
- [Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression](https://mlsanity.com/paper/2605.08475/) (2026)
- [Theory on Attention Dynamics for Out-of-Distribution In-Context Learning](https://mlsanity.com/paper/2609.36448/) (2026)

## Abstract (arXiv)

A striking property of transformers is their ability to perform in-context learning (ICL), a machine learning framework in which the learner is presented with a novel context during inference implicitly through some data, and tasked with making a prediction in that context. As such, that learner must adapt to the context without additional training. We explore the role of softmax attention in an ICL setting where each context encodes a regression task. We show that an attention unit learns a window that it uses to implement a nearest-neighbors predictor adapted to the landscape of the pretraining tasks. Specifically, we show that this window widens with decreasing Lipschitzness and increasing label noise in the pretraining tasks. We also show that on low-rank, linear problems, the attention unit learns to project onto the appropriate subspace before inference. Further, we show that this adaptivity relies crucially on the softmax activation and thus cannot be replicated by the linear activation often studied in prior theoretical analyses.