arXiv subjects

Alan Fern

Publications and source records attributed to Alan Fern.

At least 73 records · Page 4Linked to original sources

arXiv2019

The Choice Function Framework for Online Policy Improvement

There are notable examples of online search improving over hand-coded or learned policies (e.g. AlphaZero) for sequential decision making. It is not clear, however, whether or not policy improvement is guaranteed for many of these approaches, even when given a perfect evaluation function and transition model. Indeed, simple counter examples show that seemingly reasonable online search procedures can hurt performance compared to the original policy. To address this issue, we introduce the choice function framework for analyzing online search procedures for policy improvement. A choice function specifies the actions to be considered at every node of a search tree, with all other actions being pruned. Our main contribution is to give sufficient conditions for stationary and non-stationary choice functions to guarantee that the value achieved by online search is no worse than the original policy. In addition, we describe a general parametric class of choice functions that satisfy those conditions and present an illustrative use case of the framework's empirical utility.

cs.AI↗

arXiv2019

Explaining Reinforcement Learning to Mere Mortals: An Empirical Study

We present a user study to investigate the impact of explanations on non-experts' understanding of reinforcement learning (RL) agents. We investigate both a common RL visualization, saliency maps (the focus of attention), and a more recent explanation type, reward-decomposition bars (predictions of future types of rewards). We designed a 124 participant, four-treatment experiment to compare participants' mental models of an RL agent in a simple Real-Time Strategy (RTS) game. Our results show that the combination of both saliency and reward bars were needed to achieve a statistically significant improvement in mental model score over the control. In addition, our qualitative analysis of the data reveals a number of effects for further study.

cs.HC↗

arXiv2018

Interactive Naming for Explaining Deep Neural Networks: A Formative Study

We consider the problem of explaining the decisions of deep neural networks for image recognition in terms of human-recognizable visual concepts. In particular, given a test set of images, we aim to explain each classification in terms of a small number of image regions, or activation maps, which have been associated with semantic concepts by a human annotator. This allows for generating summary views of the typical reasons for classifications, which can help build trust in a classifier and/or identify example types for which the classifier may not be trusted. For this purpose, we developed a user interface for "interactive naming," which allows a human annotator to manually cluster significant activation maps in a test set into meaningful groups called "visual concepts". The main contribution of this paper is a systematic study of the visual concepts produced by five human annotators using the interactive naming interface. In particular, we consider the adequacy of the concepts for explaining the classification of test-set images, correspondence of the concepts to activations of individual neurons, and the inter-annotator agreement of visual concepts. We find that a large fraction of the activation maps have recognizable visual concepts, and that there is significant agreement between the different annotators about their denotations. Our work is an exploratory study of the interplay between machine learning and human recognition mediated by visualizations of the results of learning.

cs.LG↗

arXiv2018

Learning Finite State Representations of Recurrent Policy Networks

Recurrent neural networks (RNNs) are an effective representation of control policies for a wide range of reinforcement and imitation learning problems. RNN policies, however, are particularly difficult to explain, understand, and analyze due to their use of continuous-valued memory vectors and observation features. In this paper, we introduce a new technique, Quantized Bottleneck Insertion, to learn finite representations of these vectors and features. The result is a quantized representation of the RNN that can be analyzed to improve our understanding of memory use and general behavior. We present results of this approach on synthetic environments and six Atari games. The resulting finite representations are surprisingly small in some cases, using as few as 3 discrete memory states and 10 observations for a perfect Pong policy. We also show that these finite policy representations lead to improved interpretability.

cs.LG↗

arXiv2018

Visualizing and Understanding Atari Agents

While deep reinforcement learning (deep RL) agents are effective at maximizing rewards, it is often unclear what strategies they use to do so. In this paper, we take a step toward explaining deep RL agents through a case study using Atari 2600 environments. In particular, we focus on using saliency maps to understand how an agent learns and executes a policy. We introduce a method for generating useful saliency maps and use it to show 1) what strong agents attend to, 2) whether agents are making decisions for the right or wrong reasons, and 3) how agents evolve during learning. We also test our method on non-expert human subjects and find that it improves their ability to reason about these agents. Overall, our results show that saliency information can provide significant insight into an RL agent's decisions and learning behavior.

cs.AI↗

arXiv2018

Open Category Detection with PAC Guarantees

Open category detection is the problem of detecting "alien" test instances that belong to categories or classes that were not present in the training data. In many applications, reliably detecting such aliens is central to ensuring the safety and accuracy of test set predictions. Unfortunately, there are no algorithms that provide theoretical guarantees on their ability to detect aliens under general assumptions. Further, while there are algorithms for open category detection, there are few empirical results that directly report alien detection rates. Thus, there are significant theoretical and empirical gaps in our understanding of open category detection. In this paper, we take a step toward addressing this gap by studying a simple, but practically-relevant variant of open category detection. In our setting, we are provided with a "clean" training set that contains only the target categories of interest and an unlabeled "contaminated" training set that contains a fraction $α$ of alien examples. Under the assumption that we know an upper bound on $α$, we develop an algorithm with PAC-style guarantees on the alien detection rate, while aiming to minimize false alarms. Empirical results on synthetic and standard benchmark datasets demonstrate the regimes in which the algorithm can be effective and provide a baseline for further advancements.

cs.LG↗

arXiv2017

Schema Independent Relational Learning

Learning novel concepts and relations from relational databases is an important problem with many applications in database systems and machine learning. Relational learning algorithms learn the definition of a new relation in terms of existing relations in the database. Nevertheless, the same data set may be represented under different schemas for various reasons, such as efficiency, data quality, and usability. Unfortunately, the output of current relational learning algorithms tends to vary quite substantially over the choice of schema, both in terms of learning accuracy and efficiency. This variation complicates their off-the-shelf application. In this paper, we introduce and formalize the property of schema independence of relational learning algorithms, and study both the theoretical and empirical dependence of existing algorithms on the common class of (de) composition schema transformations. We study both sample-based learning algorithms, which learn from sets of labeled examples, and query-based algorithms, which learn by asking queries to an oracle. We prove that current relational learning algorithms are generally not schema independent. For query-based learning algorithms we show that the (de) composition transformations influence their query complexity. We propose Castor, a sample-based relational learning algorithm that achieves schema independence by leveraging data dependencies. We support the theoretical results with an empirical study that demonstrates the schema dependence/independence of several algorithms on existing benchmark and real-world datasets under (de) compositions.

cs.DB↗

arXiv2017

Incorporating Feedback into Tree-based Anomaly Detection

Anomaly detectors are often used to produce a ranked list of statistical anomalies, which are examined by human analysts in order to extract the actual anomalies of interest. Unfortunately, in realworld applications, this process can be exceedingly difficult for the analyst since a large fraction of high-ranking anomalies are false positives and not interesting from the application perspective. In this paper, we aim to make the analyst's job easier by allowing for analyst feedback during the investigation process. Ideally, the feedback influences the ranking of the anomaly detector in a way that reduces the number of false positives that must be examined before discovering the anomalies of interest. In particular, we introduce a novel technique for incorporating simple binary feedback into tree-based anomaly detectors. We focus on the Isolation Forest algorithm as a representative tree-based anomaly detector, and show that we can significantly improve its performance by incorporating feedback, when compared with the baseline algorithm that does not incorporate feedback. Our technique is simple and scales well as the size of the data increases, which makes it suitable for interactive discovery of anomalies in large datasets.

cs.LG↗

arXiv2016

A Meta-Analysis of the Anomaly Detection Problem

This article provides a thorough meta-analysis of the anomaly detection problem. To accomplish this we first identify approaches to benchmarking anomaly detection algorithms across the literature and produce a large corpus of anomaly detection benchmarks that vary in their construction across several dimensions we deem important to real-world applications: (a) point difficulty, (b) relative frequency of anomalies, (c) clusteredness of anomalies, and (d) relevance of features. We apply a representative set of anomaly detection algorithms to this corpus, yielding a very large collection of experimental results. We analyze these results to understand many phenomena observed in previous work. First we observe the effects of experimental design on experimental results. Second, results are evaluated with two metrics, ROC Area Under the Curve and Average Precision. We employ statistical hypothesis testing to demonstrate the value (or lack thereof) of our benchmarks. We then offer several approaches to summarizing our experimental results, drawing several conclusions about the impact of our methodology as well as the strengths and weaknesses of some algorithms. Last, we compare results against a trivial solution as an alternate means of normalizing the reported performance of algorithms. The intended contributions of this article are many; in addition to providing a large publicly-available corpus of anomaly detection benchmarks, we provide an ontology for describing anomaly detection contexts, a methodology for controlling various aspects of benchmark creation, guidelines for future experimental design and a discussion of the many potential pitfalls of trying to measure success in this field.

cs.AI↗

arXiv2016

Approximate Policy Iteration for Budgeted Semantic Video Segmentation

This paper formulates and presents a solution to the new problem of budgeted semantic video segmentation. Given a video, the goal is to accurately assign a semantic class label to every pixel in the video within a specified time budget. Typical approaches to such labeling problems, such as Conditional Random Fields (CRFs), focus on maximizing accuracy but do not provide a principled method for satisfying a time budget. For video data, the time required by CRF and related methods is often dominated by the time to compute low-level descriptors of supervoxels across the video. Our key contribution is the new budgeted inference framework for CRF models that intelligently selects the most useful subsets of descriptors to run on subsets of supervoxels within the time budget. The objective is to maintain an accuracy as close as possible to the CRF model with no time bound, while remaining within the time budget. Our second contribution is the algorithm for learning a policy for the sparse selection of supervoxels and their descriptors for budgeted CRF inference. This learning algorithm is derived by casting our problem in the framework of Markov Decision Processes, and then instantiating a state-of-the-art policy learning algorithm known as Classification-Based Approximate Policy Iteration. Our experiments on multiple video datasets show that our learning approach and framework is able to significantly reduce computation time, and maintain competitive accuracy under varying budgets.

cs.CV↗

arXiv2015

Sequential Feature Explanations for Anomaly Detection

In many applications, an anomaly detection system presents the most anomalous data instance to a human analyst, who then must determine whether the instance is truly of interest (e.g. a threat in a security setting). Unfortunately, most anomaly detectors provide no explanation about why an instance was considered anomalous, leaving the analyst with no guidance about where to begin the investigation. To address this issue, we study the problems of computing and evaluating sequential feature explanations (SFEs) for anomaly detectors. An SFE of an anomaly is a sequence of features, which are presented to the analyst one at a time (in order) until the information contained in the highlighted features is enough for the analyst to make a confident judgement about the anomaly. Since analyst effort is related to the amount of information that they consider in an investigation, an explanation's quality is related to the number of features that must be revealed to attain confidence. One of our main contributions is to present a novel framework for large scale quantitative evaluations of SFEs, where the quality measure is based on analyst effort. To do this we construct anomaly detection benchmarks from real data sets along with artificial experts that can be simulated for evaluation. Our second contribution is to evaluate several novel explanation approaches within the framework and on traditional anomaly detection benchmarks, offering several insights into the approaches.

cs.AI↗

arXiv2014

Representation Independent Analytics Over Structured Data

Database analytics algorithms leverage quantifiable structural properties of the data to predict interesting concepts and relationships. The same information, however, can be represented using many different structures and the structural properties observed over particular representations do not necessarily hold for alternative structures. Thus, there is no guarantee that current database analytics algorithms will still provide the correct insights, no matter what structures are chosen to organize the database. Because these algorithms tend to be highly effective over some choices of structure, such as that of the databases used to validate them, but not so effective with others, database analytics has largely remained the province of experts who can find the desired forms for these algorithms. We argue that in order to make database analytics usable, we should use or develop algorithms that are effective over a wide range of choices of structural organizations. We introduce the notion of representation independence, study its fundamental properties for a wide range of data analytics algorithms, and empirically analyze the amount of representation independence of some popular database analytics algorithms. Our results indicate that most algorithms are not generally representation independent and find the characteristics of more representation independent heuristics under certain representational shifts.

cs.DB↗

arXiv2014

A Policy Switching Approach to Consolidating Load Shedding and Islanding Protection Schemes

In recent years there have been many improvements in the reliability of critical infrastructure systems. Despite these improvements, the power systems industry has seen relatively small advances in this regard. For instance, power quality deficiencies, a high number of localized contingencies, and large cascading outages are still too widespread. Though progress has been made in improving generation, transmission, and distribution infrastructure, remedial action schemes (RAS) remain non-standardized and are often not uniformly implemented across different utilities, ISOs, and RTOs. Traditionally, load shedding and islanding have been successful protection measures in restraining propagation of contingencies and large cascading outages. This paper proposes a novel, algorithmic approach to selecting RAS policies to optimize the operation of the power network during and after a contingency. Specifically, we use policy-switching to consolidate traditional load shedding and islanding schemes. In order to model and simulate the functionality of the proposed power systems protection algorithm, we conduct Monte-Carlo, time-domain simulations using Siemens PSS/E. The algorithm is tested via experiments on the IEEE-39 topology to demonstrate that the proposed approach achieves optimal power system performance during emergency situations, given a specific set of RAS policies.

eess.SY↗

arXiv2014

Coactive Learning for Locally Optimal Problem Solving

Coactive learning is an online problem solving setting where the solutions provided by a solver are interactively improved by a domain expert, which in turn drives learning. In this paper we extend the study of coactive learning to problems where obtaining a globally optimal or near-optimal solution may be intractable or where an expert can only be expected to make small, local improvements to a candidate solution. The goal of learning in this new setting is to minimize the cost as measured by the expert effort over time. We first establish theoretical bounds on the average cost of the existing coactive Perceptron algorithm. In addition, we consider new online algorithms that use cost-sensitive and Passive-Aggressive (PA) updates, showing similar or improved theoretical bounds. We provide an empirical evaluation of the learners in various domains, which show that the Perceptron based algorithms are quite effective and that unlike the case for online classification, the PA algorithms do not yield significant performance gains.

cs.LG↗

arXiv2012

Inductive Policy Selection for First-Order MDPs

We select policies for large Markov Decision Processes (MDPs) with compact first-order representations. We find policies that generalize well as the number of objects in the domain grows, potentially without bound. Existing dynamic-programming approaches based on flat, propositional, or first-order representations either are impractical here or do not naturally scale as the number of objects grows without bound. We implement and evaluate an alternative approach that induces first-order policies using training data constructed by solving small problem instances using PGraphplan (Blum & Langford, 1999). Our policies are represented as ensembles of decision lists, using a taxonomic concept language. This approach extends the work of Martin and Geffner (2000) to stochastic domains, ensemble learning, and a wider variety of problems. Empirically, we find "good" policies for several stochastic first-order MDPs that are beyond the scope of previous approaches. We also discuss the application of this work to the relational reinforcement-learning problem.

cs.AI↗

arXiv2012

Active Imitation Learning via Reduction to I.I.D. Active Learning

In standard passive imitation learning, the goal is to learn a target policy by passively observing full execution trajectories of it. Unfortunately, generating such trajectories can require substantial expert effort and be impractical in some cases. In this paper, we consider active imitation learning with the goal of reducing this effort by querying the expert about the desired action at individual states, which are selected based on answers to past queries and the learner's interactions with an environment simulator. We introduce a new approach based on reducing active imitation learning to i.i.d. active learning, which can leverage progress in the i.i.d. setting. Our first contribution, is to analyze reductions for both non-stationary and stationary policies, showing that the label complexity (number of queries) of active imitation learning can be substantially less than passive learning. Our second contribution, is to introduce a practical algorithm inspired by the reductions, which is shown to be highly effective in four test domains compared to a number of alternatives.

cs.LG↗

arXiv2012

Inferring Strategies from Limited Reconnaissance in Real-time Strategy Games

In typical real-time strategy (RTS) games, enemy units are visible only when they are within sight range of a friendly unit. Knowledge of an opponent's disposition is limited to what can be observed through scouting. Information is costly, since units dedicated to scouting are unavailable for other purposes, and the enemy will resist scouting attempts. It is important to infer as much as possible about the opponent's current and future strategy from the available observations. We present a dynamic Bayes net model of strategies in the RTS game Starcraft that combines a generative model of how strategies relate to observable quantities with a principled framework for incorporating evidence gained via scouting. We demonstrate the model's ability to infer unobserved aspects of the game from realistic observations.

cs.AI↗

arXiv2012

Batch Active Learning via Coordinated Matching

Most prior work on active learning of classifiers has focused on sequentially selecting one unlabeled example at a time to be labeled in order to reduce the overall labeling effort. In many scenarios, however, it is desirable to label an entire batch of examples at once, for example, when labels can be acquired in parallel. This motivates us to study batch active learning, which iteratively selects batches of $k>1$ examples to be labeled. We propose a novel batch active learning method that leverages the availability of high-quality and efficient sequential active-learning policies by attempting to approximate their behavior when applied for $k$ steps. Specifically, our algorithm first uses Monte-Carlo simulation to estimate the distribution of unlabeled examples selected by a sequential policy over $k$ step executions. The algorithm then attempts to select a set of $k$ examples that best matches this distribution, leading to a combinatorial optimization problem that we term "bounded coordinated matching". While we show this problem is NP-hard in general, we give an efficient greedy solution, which inherits approximation bounds from supermodular minimization theory. Our experimental results on eight benchmark datasets show that the proposed approach is highly effective

cs.LG↗