Pretrained transformer efficiently learns low-dimensional target functions in-context

• URL: http://arxiv.org/abs/2411.02544v1
• Date: Mon, 04 Nov 2024 19:24:39 GMT
• Title: Pretrained transformer efficiently learns low-dimensional target functions in-context
• Authors: Kazusato Oko, Yujin Song, Taiji Suzuki, Denny Wu,
• Abstract summary: We show that a nonlinear transformer optimized by gradient descent learns $f_*$ in-context with a prompt length that only depends on the dimension of the distribution of target functions $r$. Our result highlights the adaptivity of the pretrained transformer to low-dimensional structures of the function class, which enables sample-efficient ICL.
• Score: 40.77319247558742
• License:
• Abstract: Transformers can efficiently learn in-context from example demonstrations. Most existing theoretical analyses studied the in-context learning (ICL) ability of transformers for linear function classes, where it is typically shown that the minimizer of the pretraining loss implements one gradient descent step on the least squares objective. However, this simplified linear setting arguably does not demonstrate the statistical efficiency of ICL, since the pretrained transformer does not outperform directly solving linear regression on the test prompt. In this paper, we study ICL of a nonlinear function class via transformer with nonlinear MLP layer: given a class of \textit{single-index} target functions $f_*(\boldsymbol{x}) = \sigma_*(\langle\boldsymbol{x},\boldsymbol{\beta}\rangle)$, where the index features $\boldsymbol{\beta}\in\mathbb{R}^d$ are drawn from a $r$-dimensional subspace, we show that a nonlinear transformer optimized by gradient descent (with a pretraining sample complexity that depends on the \textit{information exponent} of the link functions $\sigma_*$) learns $f_*$ in-context with a prompt length that only depends on the dimension of the distribution of target functions $r$; in contrast, any algorithm that directly learns $f_*$ on test prompt yields a statistical complexity that scales with the ambient dimension $d$. Our result highlights the adaptivity of the pretrained transformer to low-dimensional structures of the function class, which enables sample-efficient ICL that outperforms estimators that only have access to the in-context data.

Related papers

• Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers [54.20763128054692]
  We study how a two-attention-layer transformer is trained to perform ICL on $n$-gram Markov chain data. We prove that the gradient flow with respect to a cross-entropy ICL loss converges to a limiting model.
  arXiv  Detail & Related papers  (2024-09-09T18:10:26Z)
• On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability [34.43255978863601]
  Several suggest that transformers learn a mesa-optimizer during autorere training. We show that a stronger assumption related to the moments of data is the sufficient necessary condition that the learned mesa-optimizer can perform.
  arXiv  Detail & Related papers  (2024-05-27T05:41:06Z)
• Towards Better Understanding of In-Context Learning Ability from In-Context Uncertainty Quantification [7.869708570399577]
  We consider a bi-objective prediction task of predicting both the conditional expectation $mathbbE[Y|X]$ and the conditional variance Var$(Y|X)$. Theoretically, we show that the trained Transformer reaches near Bayes-optimum, suggesting the usage of the information of the training distribution.
  arXiv  Detail & Related papers  (2024-05-24T00:08:55Z)
• How do Transformers perform In-Context Autoregressive Learning? [76.18489638049545]
  We train a Transformer model on a simple next token prediction task. We show how a trained Transformer predicts the next token by first learning $W$ in-context, then applying a prediction mapping.
  arXiv  Detail & Related papers  (2024-02-08T16:24:44Z)
• Globally Convergent Accelerated Algorithms for Multilinear Sparse Logistic Regression with $\ell_0$-constraints [2.323238724742687]
  Multilinear logistic regression serves as a powerful tool for the analysis of multidimensional data. We propose an Accelerated Proximal Alternating Minim-MLSR model to solve the $ell_0$-MLSR. We also demonstrate that APALM$+$ is globally convergent to a first-order critical point as well as to establish convergence by using the Kurdy-Lojasiewicz property.
  arXiv  Detail & Related papers  (2023-09-17T11:05:08Z)
• Transformers as Support Vector Machines [54.642793677472724]
  We establish a formal equivalence between the optimization geometry of self-attention and a hard-margin SVM problem. We characterize the implicit bias of 1-layer transformers optimized with gradient descent. We believe these findings inspire the interpretation of transformers as a hierarchy of SVMs that separates and selects optimal tokens.
  arXiv  Detail & Related papers  (2023-08-31T17:57:50Z)
• One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention [31.522320487765878]
  Recent works have empirically analyzed in-context learning. One-layer transformers with linear self-attention learn to implement one step of gradient descent.
  arXiv  Detail & Related papers  (2023-07-07T13:09:18Z)
• Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting [60.98700344526674]
  Low-complexity models such as linear function representation play a pivotal role in enabling sample-efficient reinforcement learning. In this paper, we investigate a new sampling protocol, which draws samples in an online/exploratory fashion but allows one to backtrack and revisit previous states in a controlled and infrequent manner. We develop an algorithm tailored to this setting, achieving a sample complexity that scales practicallyly with the feature dimension, the horizon, and the inverse sub-optimality gap, but not the size of the state/action space.
  arXiv  Detail & Related papers  (2021-05-17T17:22:07Z)
• Learning to extrapolate using continued fractions: Predicting the critical temperature of superconductor materials [5.905364646955811]
  In the field of Artificial Intelligence (AI) and Machine Learning (ML), the approximation of unknown target functions $y=f(mathbfx)$ is a common objective. We refer to $S$ as the training set and aim to identify a low-complexity mathematical model that can effectively approximate this target function for new instances $mathbfx$.
  arXiv  Detail & Related papers  (2020-11-27T04:57:40Z)
• Piecewise Linear Regression via a Difference of Convex Functions [50.89452535187813]
  We present a new piecewise linear regression methodology that utilizes fitting a difference of convex functions (DC functions) to the data. We empirically validate the method, showing it to be practically implementable, and to have comparable performance to existing regression/classification methods on real-world datasets.
  arXiv  Detail & Related papers  (2020-07-05T18:58:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.