Universal In-Context Approximation By Prompting Fully Recurrent Models

• URL: http://arxiv.org/abs/2406.01424v2
• Date: Thu, 10 Oct 2024 16:39:12 GMT
• Title: Universal In-Context Approximation By Prompting Fully Recurrent Models
• Authors: Aleksandar Petrov, Tom A. Lamb, Alasdair Paren, Philip H. S. Torr, Adel Bibi,
• Abstract summary: We show that RNNs, LSTMs, GRUs, Linear RNNs, and linear gated architectures can serve as universal in-context approximators. We introduce a programming language called LSRL that compiles to fully recurrent architectures.
• Score: 86.61942787684272
• License:
• Abstract: Zero-shot and in-context learning enable solving tasks without model fine-tuning, making them essential for developing generative model solutions. Therefore, it is crucial to understand whether a pretrained model can be prompted to approximate any function, i.e., whether it is a universal in-context approximator. While it was recently shown that transformer models do possess this property, these results rely on their attention mechanism. Hence, these findings do not apply to fully recurrent architectures like RNNs, LSTMs, and the increasingly popular SSMs. We demonstrate that RNNs, LSTMs, GRUs, Linear RNNs, and linear gated architectures such as Mamba and Hawk/Griffin can also serve as universal in-context approximators. To streamline our argument, we introduce a programming language called LSRL that compiles to these fully recurrent architectures. LSRL may be of independent interest for further studies of fully recurrent models, such as constructing interpretability benchmarks. We also study the role of multiplicative gating and observe that architectures incorporating such gating (e.g., LSTMs, GRUs, Hawk/Griffin) can implement certain operations more stably, making them more viable candidates for practical in-context universal approximation.

Related papers

• Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models [42.17166746027585]
  We introduce a bidirectional weighted graph-based framework to learn factorized attributes and their interrelations within complex data. Specifically, we propose a $beta$-VAE based module to extract factors as the initial nodes of the graph. By integrating these complementary modules, our model successfully achieves fine-grained, practical and unsupervised disentanglement.
  arXiv  Detail & Related papers  (2024-07-26T15:32:21Z)
• Retrieval-Enhanced Machine Learning: Synthesis and Opportunities [60.34182805429511]
  Retrieval-enhancement can be extended to a broader spectrum of machine learning (ML) This work introduces a formal framework of this paradigm, Retrieval-Enhanced Machine Learning (REML), by synthesizing the literature in various domains in ML with consistent notations which is missing from the current literature. The goal of this work is to equip researchers across various disciplines with a comprehensive, formally structured framework of retrieval-enhanced models, thereby fostering interdisciplinary future research.
  arXiv  Detail & Related papers  (2024-07-17T20:01:21Z)
• In-Context Language Learning: Architectures and Algorithms [73.93205821154605]
  We study ICL through the lens of a new family of model problems we term in context language learning (ICLL) We evaluate a diverse set of neural sequence models on regular ICLL tasks.
  arXiv  Detail & Related papers  (2024-01-23T18:59:21Z)
• Learning Interpretable Rules for Scalable Data Representation and Classification [11.393431987232425]
  Rule-based Learner Representation (RRL) learns interpretable non-fuzzy rules for data representation and classification. RRL can be easily adjusted to obtain a trade-off between classification accuracy and model complexity for different scenarios.
  arXiv  Detail & Related papers  (2023-10-22T15:55:58Z)
• Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues [32.783917920167205]
  We show that combining architectures with both real or complex linear diagonal recurrences leads to arbitrarily precise approximation of sequence-to-sequence maps. We prove that employing complex eigenvalues near unit disk - i.e., the most successful strategy in S4 - greatly helps the RNN in storing information.
  arXiv  Detail & Related papers  (2023-07-21T20:09:06Z)
• Large Language Models as General Pattern Machines [64.75501424160748]
  We show that pre-trained large language models (LLMs) are capable of autoregressively completing complex token sequences. Surprisingly, pattern completion proficiency can be partially retained even when the sequences are expressed using tokens randomly sampled from the vocabulary. In this work, we investigate how these zero-shot capabilities may be applied to problems in robotics.
  arXiv  Detail & Related papers  (2023-07-10T17:32:13Z)
• Rethinking Log Odds: Linear Probability Modelling and Expert Advice in Interpretable Machine Learning [8.831954614241234]
  We introduce a family of interpretable machine learning models, with two broad additions: Linearised Additive Models (LAMs) and SubscaleHedge. LAMs replace the ubiquitous logistic link function in General Additive Models (GAMs); and SubscaleHedge is an expert advice algorithm for combining base models trained on subsets of features called subscales.
  arXiv  Detail & Related papers  (2022-11-11T17:21:57Z)
• A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning [132.45959478064736]
  We propose a general framework that unifies model-based and model-free reinforcement learning. We propose a novel estimation function with decomposable structural properties for optimization-based exploration. Under our framework, a new sample-efficient algorithm namely OPtimization-based ExploRation with Approximation (OPERA) is proposed.
  arXiv  Detail & Related papers  (2022-09-30T17:59:16Z)
• Scalable Rule-Based Representation Learning for Interpretable Classification [12.736847587988853]
  Rule-based Learner Representation (RRL) learns interpretable non-fuzzy rules for data representation and classification. RRL can be easily adjusted to obtain a trade-off between classification accuracy and model complexity for different scenarios.
  arXiv  Detail & Related papers  (2021-09-30T13:07:42Z)
• Reinforcement Learning as One Big Sequence Modeling Problem [84.84564880157149]
  Reinforcement learning (RL) is typically concerned with estimating single-step policies or single-step models. We view RL as a sequence modeling problem, with the goal being to predict a sequence of actions that leads to a sequence of high rewards.
  arXiv  Detail & Related papers  (2021-06-03T17:58:51Z)

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.