Ideal Abstractions for Decision-Focused Learning
- URL: http://arxiv.org/abs/2303.17062v1
- Date: Wed, 29 Mar 2023 23:31:32 GMT
- Title: Ideal Abstractions for Decision-Focused Learning
- Authors: Michael Poli, Stefano Massaroli, Stefano Ermon, Bryan Wilder, Eric
Horvitz
- Abstract summary: 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.
- Score: 108.15241246054515
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present a methodology for formulating simplifying abstractions in machine
learning systems by identifying and harnessing the utility structure of
decisions. Machine learning tasks commonly involve high-dimensional output
spaces (e.g., predictions for every pixel in an image or node in a graph), even
though a coarser output would often suffice for downstream decision-making
(e.g., regions of an image instead of pixels). Developers often hand-engineer
abstractions of the output space, but numerous abstractions are possible and it
is unclear how the choice of output space for a model impacts its usefulness in
downstream decision-making. We propose a method that configures the output
space automatically in order to minimize the loss of decision-relevant
information. Taking a geometric perspective, we formulate a step of the
algorithm as a projection of the probability simplex, termed fold, that
minimizes the total loss of decision-related information in the H-entropy
sense. Crucially, learning in the abstracted outcome space requires less data,
leading to a net improvement in decision quality. We demonstrate the method in
two domains: data acquisition for deep neural network training and a
closed-loop wildfire management task.
Related papers
- Explainable Data-Driven Optimization: From Context to Decision and Back
Again [76.84947521482631]
Data-driven optimization uses contextual information and machine learning algorithms to find solutions to decision problems with uncertain parameters.
We introduce a counterfactual explanation methodology tailored to explain solutions to data-driven problems.
We demonstrate our approach by explaining key problems in operations management such as inventory management and routing.
arXiv Detail & Related papers (2023-01-24T15:25:16Z) - AMS-Net: Adaptive Multiscale Sparse Neural Network with Interpretable
Basis Expansion for Multiphase Flow Problems [8.991619150027267]
We propose an adaptive sparse learning algorithm that can be applied to learn the physical processes and obtain a sparse representation of the solution given a large snapshot space.
The information of the basis functions are incorporated in the loss function, which minimizes the differences between the downscaled reduced order solutions and reference solutions at multiple time steps.
More numerical tests are performed on two-phase multiscale flow problems to show the capability and interpretability of the proposed method on complicated applications.
arXiv Detail & Related papers (2022-07-24T13:12:43Z) - DPDR: A novel machine learning method for the Decision Process for
Dimensionality Reduction [1.827510863075184]
It is often confusing to find a suitable method to reduce dimensionality in a supervised learning context.
This paper proposes a new method to choose the best dimensionality reduction method in a supervised learning context.
The main algorithms used are the Random Forest algorithms (RF), the Principal Component Analysis (PCA) algorithm, and the multilayer perceptron (MLP) neural network algorithm.
arXiv Detail & Related papers (2022-06-17T19:14:39Z) - Inducing Gaussian Process Networks [80.40892394020797]
We propose inducing Gaussian process networks (IGN), a simple framework for simultaneously learning the feature space as well as the inducing points.
The inducing points, in particular, are learned directly in the feature space, enabling a seamless representation of complex structured domains.
We report on experimental results for real-world data sets showing that IGNs provide significant advances over state-of-the-art methods.
arXiv Detail & Related papers (2022-04-21T05:27:09Z) - R(Det)^2: Randomized Decision Routing for Object Detection [64.48369663018376]
We propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection.
To facilitate effective learning, we propose randomized decision routing with node selective and associative losses.
We name this approach as the randomized decision routing for object detection, abbreviated as R(Det)$2$.
arXiv Detail & Related papers (2022-04-02T07:54:58Z) - Revisiting Point Cloud Simplification: A Learnable Feature Preserving
Approach [57.67932970472768]
Mesh and Point Cloud simplification methods aim to reduce the complexity of 3D models while retaining visual quality and relevant salient features.
We propose a fast point cloud simplification method by learning to sample salient points.
The proposed method relies on a graph neural network architecture trained to select an arbitrary, user-defined, number of points from the input space and to re-arrange their positions so as to minimize the visual perception error.
arXiv Detail & Related papers (2021-09-30T10:23:55Z) - Model-Agnostic Explanations using Minimal Forcing Subsets [11.420687735660097]
We propose a new model-agnostic algorithm to identify a minimal set of training samples that are indispensable for a given model's decision.
Our algorithm identifies such a set of "indispensable" samples iteratively by solving a constrained optimization problem.
Results show that our algorithm is an effective and easy-to-comprehend tool that helps to better understand local model behavior.
arXiv Detail & Related papers (2020-11-01T22:45:16Z) - Learning Abstract Models for Strategic Exploration and Fast Reward
Transfer [85.19766065886422]
We learn an accurate Markov Decision Process (MDP) over abstract states to avoid compounding errors.
Our approach achieves strong results on three of the hardest Arcade Learning Environment games.
We can reuse the learned abstract MDP for new reward functions, achieving higher reward in 1000x fewer samples than model-free methods trained from scratch.
arXiv Detail & Related papers (2020-07-12T03:33:50Z) - Learning Discrete State Abstractions With Deep Variational Inference [7.273663549650618]
We propose a method for learning approximate bisimulations, a type of state abstraction.
We use a deep neural encoder to map states onto continuous embeddings.
We map these embeddings onto a discrete representation using an action-conditioned hidden Markov model.
arXiv Detail & Related papers (2020-03-09T17:58:27Z)
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.