Towards a Mathematical Theory of Abstraction
- URL: http://arxiv.org/abs/2106.01826v1
- Date: Thu, 3 Jun 2021 13:23:49 GMT
- Title: Towards a Mathematical Theory of Abstraction
- Authors: Beren Millidge
- Abstract summary: We provide a precise characterisation of what an abstraction is and, perhaps more importantly, suggest how abstractions can be learnt directly from data.
Our results have deep implications for statistical inference and machine learning and could be used to develop explicit methods for learning precise kinds of abstractions directly from data.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: While the utility of well-chosen abstractions for understanding and
predicting the behaviour of complex systems is well appreciated, precisely what
an abstraction $\textit{is}$ has so far has largely eluded mathematical
formalization. In this paper, we aim to set out a mathematical theory of
abstraction. We provide a precise characterisation of what an abstraction is
and, perhaps more importantly, suggest how abstractions can be learnt directly
from data both for static datasets and for dynamical systems. We define an
abstraction to be a small set of `summaries' of a system which can be used to
answer a set of queries about the system or its behaviour. The difference
between the ground truth behaviour of the system on the queries and the
behaviour of the system predicted only by the abstraction provides a measure of
the `leakiness' of the abstraction which can be used as a loss function to
directly learn abstractions from data. Our approach can be considered a
generalization of classical statistics where we are not interested in
reconstructing `the data' in full, but are instead only concerned with
answering a set of arbitrary queries about the data. While highly theoretical,
our results have deep implications for statistical inference and machine
learning and could be used to develop explicit methods for learning precise
kinds of abstractions directly from data.
Related papers
- Bisimulation Learning [55.859538562698496]
We compute finite bisimulations of state transition systems with large, possibly infinite state space.
Our technique yields faster verification results than alternative state-of-the-art tools in practice.
arXiv Detail & Related papers (2024-05-24T17:11:27Z) - How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval? [120.49126407479717]
We propose a sketch-based image retrieval framework capable of handling sketch abstraction at varied levels.
For granularity-level abstraction understanding, we dictate that the retrieval model should not treat all abstraction-levels equally.
Our Acc.@q loss uniquely allows a sketch to narrow/broaden its focus in terms of how stringent the evaluation should be.
arXiv Detail & Related papers (2024-03-11T23:08:29Z) - Neural Causal Abstractions [63.21695740637627]
We develop a new family of causal abstractions by clustering variables and their domains.
We show that such abstractions are learnable in practical settings through Neural Causal Models.
Our experiments support the theory and illustrate how to scale causal inferences to high-dimensional settings involving image data.
arXiv Detail & Related papers (2024-01-05T02:00:27Z) - AbsPyramid: Benchmarking the Abstraction Ability of Language Models with a Unified Entailment Graph [62.685920585838616]
abstraction ability is essential in human intelligence, which remains under-explored in language models.
We present AbsPyramid, a unified entailment graph of 221K textual descriptions of abstraction knowledge.
arXiv Detail & Related papers (2023-11-15T18:11:23Z) - ShapeCoder: Discovering Abstractions for Visual Programs from
Unstructured Primitives [44.01940125080666]
We present ShapeCoder, the first system capable of taking a dataset of shapes, represented with unstructured primitives.
We show how ShapeCoder discovers a library of abstractions that capture high-level relationships, remove extraneous degrees of freedom, and achieve better dataset compression.
arXiv Detail & Related papers (2023-05-09T17:55:48Z) - Ideal Abstractions for Decision-Focused Learning [108.15241246054515]
We propose a method that configures the output space automatically in order to minimize the loss of decision-relevant information.
We demonstrate the method in two domains: data acquisition for deep neural network training and a closed-loop wildfire management task.
arXiv Detail & Related papers (2023-03-29T23:31:32Z) - Abstract Interpretation for Generalized Heuristic Search in Model-Based
Planning [50.96320003643406]
Domain-general model-based planners often derive their generality by constructing searchs through the relaxation of symbolic world models.
We illustrate how abstract interpretation can serve as a unifying framework for these abstractions, extending the reach of search to richer world models.
Theses can also be integrated with learning, allowing agents to jumpstart planning in novel world models via abstraction-derived information.
arXiv Detail & Related papers (2022-08-05T00:22:11Z) - Towards Computing an Optimal Abstraction for Structural Causal Models [16.17846886492361]
We focus on the problem of learning abstractions.
We suggest a concrete measure of information loss, and we illustrate its contribution to learning new abstractions.
arXiv Detail & Related papers (2022-08-01T14:35:57Z) - Abstracting Noisy Robot Programs [17.04153879817609]
We describe an approach to abstraction of probabilistic and dynamic systems.
Based on a variant of the situation calculus with probabilistic belief, we define a notion of bisimulation.
We obtain abstract Golog programs that omit unnecessary details and which can be translated back to a detailed program for actual execution.
arXiv Detail & Related papers (2022-04-07T16:04:19Z) - Symbolic Abstractions From Data: A PAC Learning Approach [0.42603120588176624]
Symbolic control techniques aim to satisfy complex logic specifications.
The methods used to compute symbolic abstractions require knowledge of an accurate closed-form model.
We present a new data-driven approach that does not require closed-form dynamics.
arXiv Detail & Related papers (2021-04-28T17:34:28Z) - Extracting Semantic Indoor Maps from Occupancy Grids [2.4214518935746185]
We focus on the semantic mapping of indoor environments.
We propose a method to extract an abstracted floor plan from typical grid maps using Bayesian reasoning.
We demonstrate the effectiveness of the approach using real-world data.
arXiv Detail & Related papers (2020-02-19T18:52:27Z)
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.