paper-with-me

홈 › Papers

Can Transformers Learn Full Bayesian Inference in Context?

2025-01-28 · Arik Reuter, Tim G. J. Rudner, Vincent Fortuin, David Rügamer

Transformers have emerged as the dominant architecture in the field of deep learning, with a broad range of applications and remarkable in-context learning (ICL) capabilities. While not yet fully understood, ICL has already proved to be an intriguing phenomenon, allowing transformers to learn in context -- without requiring further training. In this paper, we further advance the understanding of ICL by demonstrating that transformers can perform full Bayesian inference for commonly used statistical models in context. More specifically, we introduce a general framework that builds on ideas from prior fitted networks and continuous normalizing flows which enables us to infer complex posterior distributions for methods such as generalized linear models and latent factor models. Extensive experiments on real-world datasets demonstrate that our ICL approach yields posterior samples that are similar in quality to state-of-the-art MCMC or variational inference methods not operating in context.

📄 PDF Abstract BibTeX arXiv:2501.16825

Code (1)

arikreuter/icl_for_full_bayesian_inference 공식 구현 jax

Tasks

Bayesian InferenceIn-Context LearningVariational Inference

Methods 이 논문이 사용한 방법론

Variational Inference 설명 없음
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

In-Context Learning through the Bayesian Prism

2023-06-08 · Madhur Panwar, Kabir Ahuja, Navin Goyal

In-context learning (ICL) is one of the surprising and useful features of large language models and subject of intense research. Recently, stylized meta-learning-like ICL setups have been devised that train transformers …

Bayesian InferenceIn-Context LearningInductive BiasLanguage Modelling+2

A Bayesian Perspective on the Role of Epistemic Uncertainty for Delayed Generalization in In-Context Learning

2026-04-14 · Abdessamed Qchohi, Simone Rossi arxiv

In-context learning enables transformers to adapt to new tasks from a few examples at inference time, while grokking highlights that this generalization can emerge abruptly only after prolonged training. We study task ge…

Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers

2026-03-10 · Albus Yizhuo Li, Matthew Wicker arxiv

Foundation models are increasingly being deployed in contexts where understanding the uncertainty of their outputs is critical to ensuring responsible deployment. While Bayesian methods offer a principled approach to unc…

Bayesian Inference

Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation

2026-06-30 · Jiachun Li, David Simchi-Levi arxiv

Adaptive experiments for average treatment effects (ATE) require randomized allocations balancing valid inference with statistical efficiency. The oracle design is a covariate-dependent Neyman rule governed by unknown ar…

Bayesian Optimality of In-Context Learning with Selective State Spaces

2026-02-19 · Di Zhang, Jiaqi Xing arxiv

We propose Bayesian optimal sequential prediction as a new principle for understanding in-context learning (ICL). Unlike interpretations framing Transformers as performing implicit gradient descent, we formalize ICL as m…