Dissociating model architectures from inference computations

• URL: http://arxiv.org/abs/2507.15776v1
• Date: Mon, 21 Jul 2025 16:30:42 GMT
• Title: Dissociating model architectures from inference computations
• Authors: Noor Sajid, Johan Medrano,
• Abstract summary: We show how auto-regressive and deep temporal models differ in their treatment of non-Markovian sequence modelling.<n>We demonstrate that deep temporal computations are mimicked by autoregressive models by structuring context access during iterative inference.
• Score: 0.6906005491572401
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Parr et al., 2025 examines how auto-regressive and deep temporal models differ in their treatment of non-Markovian sequence modelling. Building on this, we highlight the need for dissociating model architectures, i.e., how the predictive distribution factorises, from the computations invoked at inference. We demonstrate that deep temporal computations are mimicked by autoregressive models by structuring context access during iterative inference. Using a transformer trained on next-token prediction, we show that inducing hierarchical temporal factorisation during iterative inference maintains predictive capacity while instantiating fewer computations. This emphasises that processes for constructing and refining predictions are not necessarily bound to their underlying model architectures.

Related papers

• Scaling Laws and Representation Learning in Simple Hierarchical Languages: Transformers vs. Convolutional Architectures [49.19753720526998]
  We derive theoretical scaling laws for neural network performance on synthetic datasets.<n>We validate that convolutional networks, whose structure aligns with that of the generative process through locality and weight sharing, enjoy a faster scaling of performance.<n>This finding clarifies the architectural biases underlying neural scaling laws and highlights how representation learning is shaped by the interaction between model architecture and the statistical properties of data.
  arXiv  Detail & Related papers  (2025-05-11T17:44:14Z)
• Enforcing Interpretability in Time Series Transformers: A Concept Bottleneck Framework [2.8470354623829577]
  We develop a framework based on Concept Bottleneck Models to enforce interpretability of time series Transformers. We modify the training objective to encourage a model to develop representations similar to predefined interpretable concepts. We find that the model performance remains mostly unaffected, while the model shows much improved interpretability.
  arXiv  Detail & Related papers  (2024-10-08T14:22:40Z)
• Approximate learning of parsimonious Bayesian context trees [0.0]
  The proposed framework is tested on synthetic and real-world data examples. It outperforms existing sequence models when fitted to real protein sequences and honeypot computer terminal sessions.
  arXiv  Detail & Related papers  (2024-07-27T11:50:40Z)
• Non-autoregressive Sequence-to-Sequence Vision-Language Models [59.445765313094434]
  We propose a parallel decoding sequence-to-sequence vision-language model that marginalizes over multiple inference paths in the decoder.<n>The model achieves performance on-par with its state-of-the-art autoregressive counterpart, but is faster at inference time.
  arXiv  Detail & Related papers  (2024-03-04T17:34:59Z)
• Structured Radial Basis Function Network: Modelling Diversity for Multiple Hypotheses Prediction [51.82628081279621]
  Multi-modal regression is important in forecasting nonstationary processes or with a complex mixture of distributions. A Structured Radial Basis Function Network is presented as an ensemble of multiple hypotheses predictors for regression problems. It is proved that this structured model can efficiently interpolate this tessellation and approximate the multiple hypotheses target distribution.
  arXiv  Detail & Related papers  (2023-09-02T01:27:53Z)
• Last layer state space model for representation learning and uncertainty quantification [0.0]
  We propose to decompose a classification or regression task in two steps: a representation learning stage to learn low-dimensional states, and a state space model for uncertainty estimation. We demonstrate how predictive distributions can be estimated on top of an existing and trained neural network, by adding a state space-based last layer. Our model accounts for the noisy data structure, due to unknown or unavailable variables, and is able to provide confidence intervals on predictions.
  arXiv  Detail & Related papers  (2023-07-04T08:37:37Z)
• ChiroDiff: Modelling chirographic data with Diffusion Models [132.5223191478268]
  We introduce a powerful model-class namely "Denoising Diffusion Probabilistic Models" or DDPMs for chirographic data. Our model named "ChiroDiff", being non-autoregressive, learns to capture holistic concepts and therefore remains resilient to higher temporal sampling rate.
  arXiv  Detail & Related papers  (2023-04-07T15:17:48Z)
• Instance-Based Neural Dependency Parsing [56.63500180843504]
  We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependency edges are extracted and labeled by comparing them to edges in a training set.
  arXiv  Detail & Related papers  (2021-09-28T05:30:52Z)
• Goal-directed Generation of Discrete Structures with Conditional Generative Models [85.51463588099556]
  We introduce a novel approach to directly optimize a reinforcement learning objective, maximizing an expected reward. We test our methodology on two tasks: generating molecules with user-defined properties and identifying short python expressions which evaluate to a given target value.
  arXiv  Detail & Related papers  (2020-10-05T20:03:13Z)
• Self-Reflective Variational Autoencoder [21.054722609128525]
  Variational Autoencoder (VAE) is a powerful framework for learning latent variable generative models. We introduce a solution, which we call self-reflective inference. We empirically demonstrate the clear advantages of matching the variational posterior to the exact posterior.
  arXiv  Detail & Related papers  (2020-07-10T05:05:26Z)
• Predicting Multidimensional Data via Tensor Learning [0.0]
  We develop a model that retains the intrinsic multidimensional structure of the dataset. To estimate the model parameters, an Alternating Least Squares algorithm is developed. The proposed model is able to outperform benchmark models present in the forecasting literature.
  arXiv  Detail & Related papers  (2020-02-11T11:57:07Z)

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.