scispace - formally typeset
Search or ask a question

Showing papers by "Thomas G. Dietterich published in 2020"


Journal ArticleDOI
TL;DR: This review aims to identify the common underlying principles and the assumptions that are often made implicitly by various methods in deep learning, and draws connections between classic “shallow” and novel deep approaches and shows how this relation might cross-fertilize or extend both directions.
Abstract: Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text. These results have sparked a renewed interest in the anomaly detection problem and led to the introduction of a great variety of new methods. With the emergence of numerous such methods, including approaches based on generative models, one-class classification, and reconstruction, there is a growing need to bring methods of this field into a systematic and unified perspective. In this review we aim to identify the common underlying principles as well as the assumptions that are often made implicitly by various methods. In particular, we draw connections between classic 'shallow' and novel deep approaches and show how this relation might cross-fertilize or extend both directions. We further provide an empirical assessment of major existing methods that is enriched by the use of recent explainability techniques, and present specific worked-through examples together with practical advice. Finally, we outline critical open challenges and identify specific paths for future research in anomaly detection.

310 citations


Journal ArticleDOI
TL;DR: This paper determines the optimal management of a synthetic landscape parameterized to represent the ecological conditions of Douglas-fir (Pseudotsuga menziesii) plantations in southwest Oregon.
Abstract: Accounting for externalities generated by fire spread is necessary for managing fire risk on landscapes with multiple owners. In this paper, we determine the optimal management of a synthetic landscape parameterized to represent the ecological conditions of Douglas-fir (Pseudotsuga menziesii) plantations in southwest Oregon. The problem is formulated as a dynamic game, where each agent maximizes their own objective without considering the welfare of the other agents. We demonstrate a method for incorporating spatial information and externalities into a dynamic optimization process. A machine-learning technique, approximate dynamic programming, is applied to determine the optimal timing and location of fuel treatments and timber harvests for each agent. The value functions we estimate explicitly account for the spatial interactions that generate fire risk. They provide a way to model the expected benefits, costs, and externalities associated with management actions that have uncertain consequences in multiple locations. The method we demonstrate is applied to analyze the effect of landscape fragmentation on landowner welfare and ecological outcomes.

10 citations


Journal ArticleDOI
TL;DR: The Active Anomaly Discovery (AAD) algorithm is described, which incorporates feedback from an expert user that labels a queried data instance as an anomaly or nominal point and approximations are presented that make the AAD algorithm much more computationally efficient while maintaining a desirable level of performance.
Abstract: Unsupervised anomaly detection algorithms search for outliers and then predict that these outliers are the anomalies. When deployed, however, these algorithms are often criticized for high false-positive and high false-negative rates. One main cause of poor performance is that not all outliers are anomalies and not all anomalies are outliers. In this article, we describe the Active Anomaly Discovery (AAD) algorithm, which incorporates feedback from an expert user that labels a queried data instance as an anomaly or nominal point. This feedback is intended to adjust the anomaly detector so that the outliers it discovers are more in tune with the expert user’s semantic understanding of the anomalies. The AAD algorithm is based on a weighted ensemble of anomaly detectors. When it receives a label from the user, it adjusts the weights on each individual ensemble member such that the anomalies rank higher in terms of their anomaly score than the outliers. The AAD approach is designed to operate in an interactive data exploration loop. In each iteration of this loop, our algorithm first selects a data instance to present to the expert as a potential anomaly and then the expert labels the instance as an anomaly or as a nominal data point. When it receives the instance label, the algorithm updates its internal model and the loop continues until a budget of B queries is spent. The goal of our approach is to maximize the total number of true anomalies in the B instances presented to the expert. We show that the AAD method performs well and in some cases doubles the number of true anomalies found compared to previous methods. In addition we present approximations that make the AAD algorithm much more computationally efficient while maintaining a desirable level of performance.

10 citations


Proceedings Article
01 Jun 2020
TL;DR: This work defines the problem of solving K-MDPs, i.e., given an original MDP and a constraint on the number of states, and proposes a family of three algorithms based on binary search with sub-optimality bounded polynomially in a precision parameter that will generate future research aiming at increasing the interpretability of MDP policies in human-operated domains.
Abstract: Markov Decision Processes (MDPs) are employed to model sequential decision-making problems under uncertainty Traditionally, algorithms to solve MDPs have focused on solving large state or action spaces With increasing applications of MDPs to human-operated domains such as conservation of biodiversity and health, developing easy-to-interpret solutions is of paramount importance to increase uptake of MDP policies Here, we define the problem of solving K-MDPs, ie, given an original MDP and a constraint on the number of states (K), generate a reduced state space MDP that minimizes the difference between the original optimal MDP value function and the reduced optimal K-MDP value function Building on existing non-transitive and transitive approximate state abstraction functions, we propose a family of three algorithms based on binary search with sub-optimality bounded polynomially in a precision parameter: ϕQ*eK-MDP-ILP, ϕQ*dK-MDP and ϕa*dK-MDP We compare these algorithms to a greedy algorithm (ϕQ*e Greedy K-MDP) and clustering approach (k-means++ K-MDP) On randomly generated MDPs and two computational sustainability MDPs, ϕa*dK-MDP outperformed all algorithms when it could find a feasible solution While numerous state abstraction problems have been proposed in the literature, this is the first time that the general problem of solving K-MDPs is suggested We hope that our work will generate future research aiming at increasing the interpretability of MDP policies in human-operated domains

5 citations


Journal ArticleDOI
TL;DR: In this article, the effects of two different types of liability regulations are examined, strict liability and negligence standards, in a model of land manager decision-making about the timing and spatial location of timber harvest and fuel treatment.
Abstract: Fire spread on forested landscapes depends on vegetation conditions across the landscape that affect the fire arrival probability and forest stand value. Landowners can control some forest characteristics that facilitate fire spread, and when a single landowner controls the entire landscape, a rational landowner accounts for spatial interactions when making management decisions. With multiple landowners, management activity by one may impact outcomes for the others. Various liability regulations have been proposed, and some enacted, to make landowners account for these impacts by changing the incentives they face. In this paper, the effects of two different types of liability regulations are examined – strict liability and negligence standards. We incorporate spatial information into a model of land manager decision-making about the timing and spatial location of timber harvest and fuel treatment. The problem is formulated as a dynamic game and solved via multi-agent approximate dynamic programming. We found that, in some cases, liability regulation can increase expected land values for individual land ownerships and for the landscape as a whole. But in other cases, it may create perverse incentives that reduce expected land value. We also showed that regulations may increase risk for individual landowners by increasing the variability of potential outcomes.

4 citations


Journal ArticleDOI
TL;DR: Probabilistic modeling for speech recognition, probabilistic relational models, the integration of multiple machine learning approaches into a task-specific system, and neural network technology are described, illustrating the Defense Advanced Research Projects Agency way of creating timely advances in a field.
Abstract: Machine learning methods provide a way for artificial intelligence systems to learn from experience. This article describes four threads of machine learning research supported and guided by the Defense Advanced Research Projects Agency — probabilistic modeling for speech recognition, probabilistic relational models, the integration of multiple machine learning approaches into a task-specific system, and neural network technology. These threads illustrate the Defense Advanced Research Projects Agency way of creating timely advances in a field.

1 citations


Posted Content
TL;DR: In this article, a three-quarter sibling regression (THS) is proposed to detect and correct for systematic errors in measurements of multiple independent random variables, which can filter the effect of systematic noise when the latent variables have observed common causes.
Abstract: Many ecological studies and conservation policies are based on field observations of species, which can be affected by systematic variability introduced by the observation process. A recently introduced causal modeling technique called 'half-sibling regression' can detect and correct for systematic errors in measurements of multiple independent random variables. However, it will remove intrinsic variability if the variables are dependent, and therefore does not apply to many situations, including modeling of species counts that are controlled by common causes. We present a technique called 'three-quarter sibling regression' to partially overcome this limitation. It can filter the effect of systematic noise when the latent variables have observed common causes. We provide theoretical justification of this approach, demonstrate its effectiveness on synthetic data, and show that it reduces systematic detection variability due to moon brightness in moth surveys.

Proceedings ArticleDOI
TL;DR: A conditional mixture model for predicting the presence and amount of rain at a weather station based on measurements at nearby stations based on evaluations on simulated faults from the Oklahoma Mesonet shows very good performance.
Abstract: Rainfall is a very important weather variable, especially for agriculture. Unfortunately, rain gauges fail frequently. This paper describes a conditional mixture model for predicting the presence and amount of rain at a weather station based on measurements at nearby stations. The model is evaluated on simulated faults (blocked rain gauges) inserted into observations from the Oklahoma Mesonet. Using the negative log-likelihood as an anomaly score, we evaluate the area under the ROC and precision-recall curves for detecting these faults. The results show very good performance.