Data-driven abstractions via adaptive refinements and a Kantorovich metric [extended version]

• URL: http://arxiv.org/abs/2303.17618v4
• Date: Mon, 30 Oct 2023 15:51:18 GMT
• Title: Data-driven abstractions via adaptive refinements and a Kantorovich metric [extended version]
• Authors: Adrien Banse, Licio Romao, Alessandro Abate, Rapha\"el M. Jungers
• Abstract summary: We introduce an adaptive refinement procedure for smart, and scalable abstraction of dynamical systems. In order to learn the optimal structure, we define a Kantorovich-inspired metric between Markov chains. We show that our method yields a much better computational complexity than using classical linear programming techniques.
• Score: 56.94699829208978
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce an adaptive refinement procedure for smart, and scalable abstraction of dynamical systems. Our technique relies on partitioning the state space depending on the observation of future outputs. However, this knowledge is dynamically constructed in an adaptive, asymmetric way. In order to learn the optimal structure, we define a Kantorovich-inspired metric between Markov chains, and we use it as a loss function. Our technique is prone to data-driven frameworks, but not restricted to. We also study properties of the above mentioned metric between Markov chains, which we believe could be of application for wider purpose. We propose an algorithm to approximate it, and we show that our method yields a much better computational complexity than using classical linear programming techniques.

Related papers

• Large-Scale OD Matrix Estimation with A Deep Learning Method [70.78575952309023]
  The proposed method integrates deep learning and numerical optimization algorithms to infer matrix structure and guide numerical optimization. We conducted tests to demonstrate the good generalization performance of our method on a large-scale synthetic dataset.
  arXiv  Detail & Related papers  (2023-10-09T14:30:06Z)
• Supervised Dimensionality Reduction and Classification with Convolutional Autoencoders [1.1164202369517053]
  A Convolutional Autoencoder is combined to simultaneously produce supervised dimensionality reduction and predictions. The resulting Latent Space can be utilized to improve traditional, interpretable classification algorithms. The proposed methodology introduces advanced explainability regarding, not only the data structure through the produced latent space, but also about the classification behaviour.
  arXiv  Detail & Related papers  (2022-08-25T15:18:33Z)
• Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiation [88.14365009076907]
  Iterative refinement is a useful paradigm for representation learning. We develop an implicit differentiation approach that improves the stability and tractability of training.
  arXiv  Detail & Related papers  (2022-07-02T10:00:35Z)
• A Hybrid Framework for Sequential Data Prediction with End-to-End Optimization [0.0]
  We investigate nonlinear prediction in an online setting and introduce a hybrid model that effectively mitigates hand-designed features and manual model selection issues. We employ a recurrent neural network (LSTM) for adaptive feature extraction from sequential data and a gradient boosting machinery (soft GBDT) for effective supervised regression. We demonstrate the learning behavior of our algorithm on synthetic data and the significant performance improvements over the conventional methods over various real life datasets.
  arXiv  Detail & Related papers  (2022-03-25T17:13:08Z)
• Optimal Variable Clustering for High-Dimensional Matrix Valued Data [3.1138411427556445]
  We propose a new latent variable model for the features arranged in matrix form. Under mild conditions, our algorithm attains clustering consistency in the high-dimensional setting. We identify the optimal weight in the sense that using this weight guarantees our algorithm to be minimax rate-optimal.
  arXiv  Detail & Related papers  (2021-12-24T02:13:04Z)
• Temporally-Consistent Surface Reconstruction using Metrically-Consistent Atlases [131.50372468579067]
  We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. We represent the reconstructed surfaces as atlases computed by a neural network, which enables us to establish correspondences between frames. Our approach outperforms state-of-the-art ones on several challenging datasets.
  arXiv  Detail & Related papers  (2021-11-12T17:48:25Z)
• Solving weakly supervised regression problem using low-rank manifold regularization [77.34726150561087]
  We solve a weakly supervised regression problem. Under "weakly" we understand that for some training points the labels are known, for some unknown, and for others uncertain due to the presence of random noise or other reasons such as lack of resources. In the numerical section, we applied the suggested method to artificial and real datasets using Monte-Carlo modeling.
  arXiv  Detail & Related papers  (2021-04-13T23:21:01Z)
• Spatial Pyramid Based Graph Reasoning for Semantic Segmentation [67.47159595239798]
  We apply graph convolution into the semantic segmentation task and propose an improved Laplacian. The graph reasoning is directly performed in the original feature space organized as a spatial pyramid. We achieve comparable performance with advantages in computational and memory overhead.
  arXiv  Detail & Related papers  (2020-03-23T12:28:07Z)
• Learning Flat Latent Manifolds with VAEs [16.725880610265378]
  We propose an extension to the framework of variational auto-encoders, where the Euclidean metric is a proxy for the similarity between data points. We replace the compact prior typically used in variational auto-encoders with a recently presented, more expressive hierarchical one. We evaluate our method on a range of data-sets, including a video-tracking benchmark.
  arXiv  Detail & Related papers  (2020-02-12T09:54:52Z)

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.