Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers

• URL: http://arxiv.org/abs/2509.22445v2
• Date: Mon, 29 Sep 2025 17:16:38 GMT
• Title: Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
• Authors: Peter Shaw, James Cohan, Jacob Eisenstein, Kristina Toutanova,
• Abstract summary: This paper introduces the theoretical notion of universalityally optimal description length objectives.<n>We show that such objectives can be tractable and differentiable by constructing and analyzing a variational objective.<n>More broadly, by providing a theoretical framework for identifying description length objectives with strong algorithmic guarantees, we outline a potential path towards training neural networks that achieve greater compression and generalization.
• Score: 12.400454043294296
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The Minimum Description Length (MDL) principle offers a formal framework for applying Occam's razor in machine learning. However, its application to neural networks such as Transformers is challenging due to the lack of a principled, universal measure for model complexity. This paper introduces the theoretical notion of asymptotically optimal description length objectives, grounded in the theory of Kolmogorov complexity. We establish that a minimizer of such an objective achieves optimal compression, for any dataset, up to an additive constant, in the limit as model resource bounds increase. We prove that asymptotically optimal objectives exist for Transformers, building on a new demonstration of their computational universality. We further show that such objectives can be tractable and differentiable by constructing and analyzing a variational objective based on an adaptive Gaussian mixture prior. Our empirical analysis shows that this variational objective selects for a low-complexity solution with strong generalization on an algorithmic task, but standard optimizers fail to find such solutions from a random initialization, highlighting key optimization challenges. More broadly, by providing a theoretical framework for identifying description length objectives with strong asymptotic guarantees, we outline a potential path towards training neural networks that achieve greater compression and generalization.

Related papers

• Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning [59.11663802446183]
  Flow and diffusion generative models can be adapted to optimize task-specific objectives while preserving prior information.<n>We introduce Flow Density Control (FDC), a simple algorithm that reduces this complex problem to a specific sequence of simpler fine-tuning tasks.<n>We derive convergence guarantees for the proposed scheme under realistic assumptions by leveraging recent understanding of mirror flows.
  arXiv  Detail & Related papers  (2025-11-27T17:19:01Z)
• Unlocking Symbol-Level Precoding Efficiency Through Tensor Equivariant Neural Network [84.22115118596741]
  We propose an end-to-end deep learning (DL) framework with low inference complexity for symbol-level precoding.<n>We show that the proposed framework captures substantial performance gains of optimal SLP, while achieving an approximately 80-times speedup over conventional methods.
  arXiv  Detail & Related papers  (2025-10-02T15:15:50Z)
• Understanding Inverse Reinforcement Learning under Overparameterization: Non-Asymptotic Analysis and Global Optimality [52.906438147288256]
  We show that our algorithm can identify the globally optimal reward and policy under certain neural network structures.<n>This is the first IRL algorithm with a non-asymptotic convergence guarantee that provably achieves global optimality.
  arXiv  Detail & Related papers  (2025-03-22T21:16:08Z)
• Pseudo-Bayesian Optimization [7.556071491014536]
  We study an axiomatic framework that elicits the minimal requirements to guarantee black-box optimization convergence.<n>We show how using simple local regression, and a suitable "randomized prior" construction to quantify uncertainty, not only guarantees convergence but also consistently outperforms state-of-the-art benchmarks.
  arXiv  Detail & Related papers  (2023-10-15T07:55:28Z)
• End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes [52.818579746354665]
  This paper proposes the first end-to-end differentiable meta-BO framework that generalises neural processes to learn acquisition functions via transformer architectures. We enable this end-to-end framework with reinforcement learning (RL) to tackle the lack of labelled acquisition data.
  arXiv  Detail & Related papers  (2023-05-25T10:58:46Z)
• Structured Optimal Variational Inference for Dynamic Latent Space Models [16.531262817315696]
  We consider a latent space model for dynamic networks, where our objective is to estimate the pairwise inner products plus the intercept of the latent positions. To balance posterior inference and computational scalability, we consider a structured mean-field variational inference framework.
  arXiv  Detail & Related papers  (2022-09-29T22:10:42Z)
• Efficient Methods for Structured Nonconvex-Nonconcave Min-Max Optimization [98.0595480384208]
  We propose a generalization extraient spaces which converges to a stationary point. The algorithm applies not only to general $p$-normed spaces, but also to general $p$-dimensional vector spaces.
  arXiv  Detail & Related papers  (2020-10-31T21:35:42Z)
• Efficient and Sparse Neural Networks by Pruning Weights in a Multiobjective Learning Approach [0.0]
  We propose a multiobjective perspective on the training of neural networks by treating its prediction accuracy and the network complexity as two individual objective functions. Preliminary numerical results on exemplary convolutional neural networks confirm that large reductions in the complexity of neural networks with neglibile loss of accuracy are possible.
  arXiv  Detail & Related papers  (2020-08-31T13:28:03Z)
• Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization [93.78811018928583]
  This paper provides a framework to analyze the convergence of federated heterogeneous optimization algorithms. We propose FedNova, a normalized averaging method that eliminates objective inconsistency while preserving fast error convergence.
  arXiv  Detail & Related papers  (2020-07-15T05:01:23Z)
• Neural Control Variates [71.42768823631918]
  We show that a set of neural networks can face the challenge of finding a good approximation of the integrand. We derive a theoretically optimal, variance-minimizing loss function, and propose an alternative, composite loss for stable online training in practice. Specifically, we show that the learned light-field approximation is of sufficient quality for high-order bounces, allowing us to omit the error correction and thereby dramatically reduce the noise at the cost of negligible visible bias.
  arXiv  Detail & Related papers  (2020-06-02T11:17:55Z)

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.