Compositional Abstraction Error and a Category of Causal Models

• URL: http://arxiv.org/abs/2103.15758v1
• Date: Mon, 29 Mar 2021 16:48:12 GMT
• Title: Compositional Abstraction Error and a Category of Causal Models
• Authors: Eigil F. Rischel, Sebastian Weichwald
• Abstract summary: We argue that compositionality is a desideratum for model transformations and the associated errors. We develop a framework for model transformations and abstractions with a notion of error that is compositional.
• Score: 2.291640606078406
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Interventional causal models describe joint distributions over some variables used to describe a system, one for each intervention setting. They provide a formal recipe for how to move between joint distributions and make predictions about the variables upon intervening on the system. Yet, it is difficult to formalise how we may change the underlying variables used to describe the system, say from fine-grained to coarse-grained variables. Here, we argue that compositionality is a desideratum for model transformations and the associated errors. We develop a framework for model transformations and abstractions with a notion of error that is compositional: when abstracting a reference model M modularly, first obtaining M' and then further simplifying that to obtain M'', then the composite transformation from M to M'' exists and its error can be bounded by the errors incurred by each individual transformation step. Category theory, the study of mathematical objects via the compositional transformations between them, offers a natural language for developing our framework. We introduce a category of finite interventional causal models and, leveraging theory of enriched categories, prove that our framework enjoys the desired compositionality properties.

Related papers

• AutoBayes: A Compositional Framework for Generalized Variational Inference [0.0]
  We introduce a new compositional framework for generalized variational inference. We explain that exact Bayesian inference and the loss functions typical of variational inference satisfy chain rules akin to that of reverse-mode automatic differentiation.
  arXiv  Detail & Related papers  (2025-03-24T12:05:45Z)
• Shape Arithmetic Expressions: Advancing Scientific Discovery Beyond Closed-Form Equations [56.78271181959529]
  Generalized Additive Models (GAMs) can capture non-linear relationships between variables and targets, but they cannot capture intricate feature interactions. We propose Shape Expressions Arithmetic ( SHAREs) that fuses GAM's flexible shape functions with the complex feature interactions found in mathematical expressions. We also design a set of rules for constructing SHAREs that guarantee transparency of the found expressions beyond the standard constraints.
  arXiv  Detail & Related papers  (2024-04-15T13:44:01Z)
• A Fixed-Point Approach for Causal Generative Modeling [20.88890689294816]
  We propose a novel formalism for describing Structural Causal Models (SCMs) as fixed-point problems on causally ordered variables. We establish the weakest known conditions for their unique recovery given the topological ordering (TO)
  arXiv  Detail & Related papers  (2024-04-10T12:29:05Z)
• Representation Surgery for Multi-Task Model Merging [57.63643005215592]
  Multi-task learning (MTL) compresses the information from multiple tasks into a unified backbone to improve computational efficiency and generalization. Recent work directly merges multiple independently trained models to perform MTL instead of collecting their raw data for joint training. By visualizing the representation distribution of existing model merging schemes, we find that the merged model often suffers from the dilemma of representation bias.
  arXiv  Detail & Related papers  (2024-02-05T03:39:39Z)
• HiPerformer: Hierarchically Permutation-Equivariant Transformer for Time Series Forecasting [56.95572957863576]
  We propose a hierarchically permutation-equivariant model that considers both the relationship among components in the same group and the relationship among groups. The experiments conducted on real-world data demonstrate that the proposed method outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-14T05:11:52Z)
• Quantifying Consistency and Information Loss for Causal Abstraction Learning [16.17846886492361]
  We introduce a family of interventional measures that an agent may use to evaluate such a trade-off. We consider four measures suited for different tasks, analyze their properties, and propose algorithms to evaluate and learn causal abstractions.
  arXiv  Detail & Related papers  (2023-05-07T19:10:28Z)
• On the Interventional Kullback-Leibler Divergence [11.57430292133273]
  We introduce the Interventional Kullback-Leibler divergence to quantify both structural and distributional differences between causal models. We propose a sufficient condition on the intervention targets to identify subsets of observed variables on which the models provably agree or disagree.
  arXiv  Detail & Related papers  (2023-02-10T17:03:29Z)
• Syntax-guided Neural Module Distillation to Probe Compositionality in Sentence Embeddings [0.0]
  We construct a neural module net based on its syntax parse and train it end-to-end to approximate the sentence's embedding. We find differences in the distillability of various sentence embedding models that broadly correlate with their performance. Preliminary evidence that much syntax-guided composition in sentence embedding models is linear.
  arXiv  Detail & Related papers  (2023-01-21T19:42:02Z)
• Recursive Monte Carlo and Variational Inference with Auxiliary Variables [64.25762042361839]
  Recursive auxiliary-variable inference (RAVI) is a new framework for exploiting flexible proposals. RAVI generalizes and unifies several existing methods for inference with expressive expressive families. We show RAVI's design framework and theorems by using them to analyze and improve upon Salimans et al.'s Markov Chain Variational Inference.
  arXiv  Detail & Related papers  (2022-03-05T23:52:40Z)
• Surrogate Modeling for Physical Systems with Preserved Properties and Adjustable Tradeoffs [0.0]
  We present a model-based and a data-driven strategy to generate surrogate models. The latter generates interpretable surrogate models by fitting artificial relations to a presupposed topological structure. Our framework is compatible with various spatial discretization schemes for distributed parameter models.
  arXiv  Detail & Related papers  (2022-02-02T17:07:02Z)
• Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective [72.55093886515824]
  We introduce a causal formalism of motion forecasting, which casts the problem as a dynamic process with three groups of latent variables. We devise a modular architecture that factorizes the representations of invariant mechanisms and style confounders to approximate a causal graph. Experiment results on synthetic and real datasets show that our three proposed components significantly improve the robustness and reusability of the learned motion representations.
  arXiv  Detail & Related papers  (2021-11-29T18:59:09Z)
• Learning Invariances for Interpretability using Supervised VAE [0.0]
  We learn model invariances as a means of interpreting a model. We propose a supervised form of variational auto-encoders (VAEs) We show how combining our model with feature attribution methods it is possible to reach a more fine-grained understanding about the decision process of the model.
  arXiv  Detail & Related papers  (2020-07-15T10:14:16Z)
• A Critical View of the Structural Causal Model [89.43277111586258]
  We show that one can identify the cause and the effect without considering their interaction at all. We propose a new adversarial training method that mimics the disentangled structure of the causal model. Our multidimensional method outperforms the literature methods on both synthetic and real world datasets.
  arXiv  Detail & Related papers  (2020-02-23T22:52:28Z)

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.