Understanding with toy surrogate models in machine learning

• URL: http://arxiv.org/abs/2410.05675v1
• Date: Tue, 8 Oct 2024 04:22:28 GMT
• Title: Understanding with toy surrogate models in machine learning
• Authors: Andrés Páez,
• Abstract summary: Some of the simple surrogate models used to understand opaque machine learning (ML) models bear some resemblance to scientific toy models. This paper provides an account of what it means to understand an opaque ML model globally with the aid of such simple models.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In the natural and social sciences, it is common to use toy models -- extremely simple and highly idealized representations -- to understand complex phenomena. Some of the simple surrogate models used to understand opaque machine learning (ML) models, such as rule lists and sparse decision trees, bear some resemblance to scientific toy models. They allow non-experts to understand how an opaque ML model works globally via a much simpler model that highlights the most relevant features of the input space and their effect on the output. The obvious difference is that the common target of a toy and a full-scale model in the sciences is some phenomenon in the world, while the target of a surrogate model is another model. This essential difference makes toy surrogate models (TSMs) a new object of study for theories of understanding, one that is not easily accommodated under current analyses. This paper provides an account of what it means to understand an opaque ML model globally with the aid of such simple models.

Related papers

• The Universality Lens: Why Even Highly Over-Parametrized Models Learn Well [4.2466572124752995]
  We study a Bayesian mixture with log-loss and (almost) uniform prior over an expansive hypothesis class.<n>Key result shows that the learner's regret is not determined by the overall size of the hypothesis class.<n>Results apply broadly across online, batch, and supervised learning settings.
  arXiv  Detail & Related papers  (2025-06-09T11:32:31Z)
• What Matters for Model Merging at Scale? [94.26607564817786]
  Model merging aims to combine multiple expert models into a more capable single model. Previous studies have primarily focused on merging a few small models. This study systematically evaluates the utility of model merging at scale.
  arXiv  Detail & Related papers  (2024-10-04T17:17:19Z)
• LLAVADI: What Matters For Multimodal Large Language Models Distillation [77.73964744238519]
  In this work, we do not propose a new efficient model structure or train small-scale MLLMs from scratch. Our studies involve training strategies, model choices, and distillation algorithms in the knowledge distillation process. By evaluating different benchmarks and proper strategy, even a 2.7B small-scale model can perform on par with larger models with 7B or 13B parameters.
  arXiv  Detail & Related papers  (2024-07-28T06:10:47Z)
• Direct and inverse modeling of soft robots by learning a condensed FEM model [3.4696964555947694]
  We propose a learning-based approach to obtain a compact but sufficiently rich mechanical representation. We show how to couple some models learned individually in particular on an example of a gripper composed of two soft fingers. This work opens new perspectives, namely for the embedded control of soft robots, but also for their design.
  arXiv  Detail & Related papers  (2023-07-21T08:07:16Z)
• Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
  We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost. Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
  arXiv  Detail & Related papers  (2023-03-13T16:00:31Z)
• Synthetic Model Combination: An Instance-wise Approach to Unsupervised Ensemble Learning [92.89846887298852]
  Consider making a prediction over new test data without any opportunity to learn from a training set of labelled data. Give access to a set of expert models and their predictions alongside some limited information about the dataset used to train them.
  arXiv  Detail & Related papers  (2022-10-11T10:20:31Z)
• Scientific Inference With Interpretable Machine Learning: Analyzing Models to Learn About Real-World Phenomena [4.312340306206884]
  Interpretable machine learning offers a solution by analyzing models holistically to derive interpretations. Current IML research is focused on auditing ML models rather than leveraging them for scientific inference. We present a framework for designing IML methods-termed 'property descriptors' that illuminate not just the model, but also the phenomenon it represents.
  arXiv  Detail & Related papers  (2022-06-11T10:13:21Z)
• Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvement [75.00655434905417]
  Explainable Artificial Intelligence (XAI) is an emerging research field bringing transparency to highly complex machine learning (ML) models. This paper offers a comprehensive overview over techniques that apply XAI practically for improving various properties of ML models. We show empirically through experiments on toy and realistic settings how explanations can help improve properties such as model generalization ability or reasoning.
  arXiv  Detail & Related papers  (2022-03-15T15:44:28Z)
• Automated Dissipation Control for Turbulence Simulation with Shell Models [1.675857332621569]
  The application of machine learning (ML) techniques, especially neural networks, has seen tremendous success at processing images and language. In this work we construct a strongly simplified representation of turbulence by using the Gledzer-Ohkitani-Yamada shell model. We propose an approach that aims to reconstruct statistical properties of turbulence such as the self-similar inertial-range scaling.
  arXiv  Detail & Related papers  (2022-01-07T15:03:52Z)
• Building Accurate Simple Models with Multihop [13.182955266765653]
  We propose a meta-approach where we transfer information from the complex model to the simple model. Our approach can transfer information between consecutive models in the sequence using any of the previously mentioned approaches. In the experiments on real data, we observe that we get consistent gains for different choices of models over 1-hop.
  arXiv  Detail & Related papers  (2021-09-14T20:39:11Z)
• Model-agnostic multi-objective approach for the evolutionary discovery of mathematical models [55.41644538483948]
  In modern data science, it is more interesting to understand the properties of the model, which parts could be replaced to obtain better results. We use multi-objective evolutionary optimization for composite data-driven model learning to obtain the algorithm's desired properties.
  arXiv  Detail & Related papers  (2021-07-07T11:17:09Z)
• Lifting Interpretability-Performance Trade-off via Automated Feature Engineering [5.802346990263708]
  Complex black-box predictive models may have high performance, but lack of interpretability causes problems. We propose a method that uses elastic black-boxes as surrogate models to create a simpler, less opaque, yet still accurate and interpretable glass-box models.
  arXiv  Detail & Related papers  (2020-02-11T09:16:45Z)

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.