paper-with-me

홈 › Papers

Softmax $\geq$ Linear: Transformers may learn to classify in-context by kernel gradient descent

2025-10-12 · Sara Dragutinović, Andrew M. Saxe, Aaditya K. Singh arxiv

The remarkable ability of transformers to learn new concepts solely by reading examples within the input prompt, termed in-context learning (ICL), is a crucial aspect of intelligent behavior. Here, we focus on understanding the learning algorithm transformers use to learn from context. Existing theoretical work, often based on simplifying assumptions, has primarily focused on linear self-attention and continuous regression tasks, finding transformers can learn in-context by gradient descent. Given that transformers are typically trained on discrete and complex tasks, we bridge the gap from this existing work to the setting of classification, with non-linear (importantly, softmax) activation. We find that transformers still learn to do gradient descent in-context, though on functionals in the kernel feature space and with a context-adaptive learning rate in the case of softmax transformer. These theoretical findings suggest a greater adaptability to context for softmax attention, which we empirically verify and study through ablations. Overall, we hope this enhances theoretical understanding of in-context learning algorithms in more realistic settings, pushes forward our intuitions and enables further theory bridging to larger models.

📄 PDF Abstract BibTeX arXiv:2510.10425

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization

2026-07-01 · Peilin Liu, Ding-Xuan Zhou arxiv

Transformer-based large models have demonstrated remarkable generalization abilities across different tasks by leveraging a context-aware attention module for in-context learning. With richer context, transformers adapt …

Domain Generalization

The Closeness of In-Context Learning and Weight Shifting for Softmax Regression

2023-04-26 · Shuai Li, Zhao Song, Yu Xia, Tong Yu 외

Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related or even job-related tasks. The attention mechanism in the T…

In-Context Learningregression

Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression

2026-05-08 · Mingsong Yan, Dongyang Li, Charles Kulick, Sui Tang arxiv

Mechanistic accounts of in-context learning (ICL) have identified iterative algorithms for linear regression and related linear prediction tasks, often using linear or ReLU attention variants. For nonlinear ICL, prior wo…

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

2024-02-18 · Liam Collins, Advait Parulekar, Aryan Mokhtari, Sujay Sanghavi 외

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…

In-Context Learning

Conformal Transformations for Symmetric Power Transformers

2025-03-05 · Saurabh Kumar, Jacob Buckman, Carles Gelada, Sean Zhang

Transformers with linear attention offer significant computational advantages over softmax-based transformers but often suffer from degraded performance. The symmetric power (sympow) transformer, a particular type of lin…