paper-with-me

Papers

Transformers As Approximations of Solomonoff Induction

2024-08-22 · Nathan Young, Michael Witbrock

Solomonoff Induction is an optimal-in-the-limit unbounded algorithm for sequence prediction, representing a Bayesian mixture of every computable probability distribution and performing close to optimally in predicting any computable sequence. Being an optimal form of computational sequence prediction, it seems plausible that it may be used as a model against which other methods of sequence prediction might be compared. We put forth and explore the hypothesis that Transformer models - the basis of Large Language Models - approximate Solomonoff Induction better than any other extant sequence prediction method. We explore evidence for and against this hypothesis, give alternate hypotheses that take this evidence into account, and outline next steps for modelling Transformers and other kinds of AI in this way.

📄 PDF Abstract BibTeX arXiv:2408.12065

Code (0)

등록된 구현이 없습니다.

Tasks

Prediction

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
Multi-Head Attention 설명 없음
Adam 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

Solomonoff Induction Violates Nicod's Criterion

2015-07-15 · Jan Leike, Marcus Hutter

Nicod's criterion states that observing a black raven is evidence for the hypothesis H that all ravens are black. We show that Solomonoff induction does not satisfy Nicod's criterion: there are time steps in which observ…

On the Computability of Solomonoff Induction and Knowledge-Seeking

2015-07-15 · Jan Leike, Marcus Hutter

Solomonoff induction is held as a gold standard for learning, but it is known to be incomputable. We quantify its incomputability by placing various flavors of Solomonoff's prior M in the arithmetical hierarchy. We also …

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Large Language Models as Computable Approximations to Solomonoff Induction

2025-05-21 · Jun Wan, Lingrui Mei

The rapid advancement of large language models (LLMs) calls for a rigorous theoretical framework to explain their empirical success. While significant progress has been made in understanding LLM behaviors, existing theor…

Few-Shot LearningIn-Context Learningtext-classificationText Classification

A Dilemma for Solomonoff Prediction

2022-06-13 · Sven Neth

The framework of Solomonoff prediction assigns prior probability to hypotheses inversely proportional to their Kolmogorov complexity. There are two well-known problems. First, the Solomonoff prior is relative to a choice…

Prediction

Ultimate Intelligence Part I: Physical Completeness and Objectivity of Induction

2015-01-03 · Eray Özkural

We propose that Solomonoff induction is complete in the physical sense via several strong physical arguments. We also argue that Solomonoff induction is fully applicable to quantum mechanics. We show how to choose an obj…