Exponentiated gradient algorithms for conditional random fields and max-margin Markov Networks

Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of parameters in these models is therefore an important problem, and becomes a key factor when learning from very large data sets. This paper describes exponentiated gradient (EG) algorithms for training such models, where EG updates are applied to the convex dual of either the log-linear or max-margin objective function; the dual in both the log-linear and max-margin cases corresponds to minimizing a convex function with simplex constraints. We study both batch and online variants of the algorithm, and provide rates of convergence for both cases. In the max-margin case, O(1/ε) EG updates are required to reach a given accuracy ε in the dual; in contrast, for log-linear models only O(log(1/ε)) updates are required. For both the max-margin and log-linear cases, our bounds suggest that the online EG algorithm requires a factor of n less computation to reach a desired accuracy than the batch EG algorithm, where n is the number of training examples. Our experiments confirm that the online algorithms are much faster than the batch algorithms in practice. We describe how the EG updates factor in a convenient way for structured prediction problems, allowing the algorithms to be efficiently applied to problems such as sequence learning or natural language parsing. We perform extensive evaluation of the algorithms, comparing them to L-BFGS and stochastic gradient descent for log-linear models, and to SVM-Struct for max-margin models. The algorithms are applied to a multi-class problem as well as to a more complex large-scale parsing task. In all these settings, the EG algorithms presented here outperform the other methods.

Sparseness vs estimating conditional probabilities : some asymptotic results

One of the nice properties of kernel classifiers such as SVMs is that they often produce sparse solutions. However, the decision functions of these classifiers cannot always be used to estimate the conditional probability of the class label. We investigate the relationship between these two properties and show that these are intimately related: sparseness does not occur when the conditional probabilities can be unambiguously estimated. We consider a family of convex loss functions and derive sharp asymptotic results for the fraction of data that becomes support vectors. This enables us to characterize the exact trade-off between sparseness and the ability to estimate conditional probabilities for these loss functions.

The Bayesian conditional independence model for measurement error: applications in ecology

The measurement error model is a well established statistical method for regression problems in medical sciences, although rarely used in ecological studies. While the situations in which it is appropriate may be less common in ecology, there are instances in which there may be benefits in its use for prediction and estimation of parameters of interest. We have chosen to explore this topic using a conditional independence model in a Bayesian framework using a Gibbs sampler, as this gives a great deal of flexibility, allowing us to analyse a number of different models without losing generality. Using simulations and two examples, we show how the conditional independence model can be used in ecology, and when it is appropriate.

An infinite-horizon robust filter for uncertain hidden Markov Models with conditional relative entropy constraints

We consider a robust filtering problem for uncertain discrete-time, homogeneous, first-order, finite-state hidden Markov models (HMMs). The class of uncertain HMMs considered is described by a conditional relative entropy constraint on measures perturbed from a nominal regular conditional probability distribution given the previous posterior state distribution and the latest measurement. Under this class of perturbations, a robust infinite horizon filtering problem is first formulated as a constrained optimization problem before being transformed via variational results into an unconstrained optimization problem; the latter can be elegantly solved using a risk-sensitive information-state based filtering.

A conditional retransmission enabled transport protocol for real-time networked control systems

Real-time networked control systems (NCSs) over data networks are being increasingly implemented on a massive scale in industrial applications. Along with this trend, wireless network technologies have been promoted for modern wireless NCSs (WNCSs). However, popular wireless network standards such as IEEE 802.11/15/16 are not designed for real-time communications. Key issues in real-time applications include limited transmission reliability and poor transmission delay performance. Considering the unique features of real-time control systems, this paper develops a conditional retransmission enabled transport protocol (CRETP) to improve the delay performance of the transmission control protocol (TCP) and also the reliability performance of the user datagram protocol (UDP) and its variants. Key features of the CRETP include a connectionless mechanism with acknowledgement (ACK), conditional retransmission and detection of ineffective data packets on the receiver side.

Expert elicitation into Bayesian networks, Part 4 of 4: eliciting a conditional probability table

An introduction to eliciting a conditional probability table in a Bayesian Network model, highlighting three efficient methods for populating a CPT.

Conditional corruption

In this paper we discuss whether corruption is contagious and whether conditional cooperation matters. We use the notion of “conditional corruption” for these effects. We analyze whether the justifiability to be corrupt is influenced by the perceived activities of others. Moreover, we also explore whether – and to what extent – group dynamics or socialization and past experiences affect corruption. We present evidence using two data sets at the micro level and a large macro level international panel data set. The results indicate that the willingness to engage in corruption is influenced by the perceived activities of peers and other individuals. Moreover, the panel data set at the macro level indicates that the past level of corruption has a strong impact on the current corruption level.

Sufficiently informative measurements for stability of approximate conditional mean estimates

This paper establishes sufficient conditions to bound the error in perturbed conditional mean estimates derived from a perturbed model (only the scalar case is shown in this paper but a similar result is expected to hold for the vector case). The results established here extend recent stability results on approximating information state filter recursions to stability results on the approximate conditional mean estimates. The presented filter stability results provide bounds for a wide variety of model error situations.

Social signal processing for pain monitoring using a hidden conditional random field

utomatic pain monitoring has the potential to greatly improve patient diagnosis and outcomes by providing a continuous objective measure. One of the most promising methods is to do this via automatically detecting facial expressions. However, current approaches have failed due to their inability to: 1) integrate the rigid and non-rigid head motion into a single feature representation, and 2) incorporate the salient temporal patterns into the classification stage. In this paper, we tackle the first problem by developing a “histogram of facial action units” representation using Active Appearance Model (AAM) face features, and then utilize a Hidden Conditional Random Field (HCRF) to overcome the second issue. We show that both of these methods improve the performance on the task of pain detection in sequence level compared to current state-of-the-art-methods on the UNBC-McMaster Shoulder Pain Archive.

Identify disorders in health records using Conditional Random Fields and Metamap: AEHRC at ShARe/CLEF 2013 eHealth Evaluation Lab Task 1

The Australian e-Health Research Centre (AEHRC) recently participated in the ShARe/CLEF eHealth Evaluation Lab Task 1. The goal of this task is to individuate mentions of disorders in free-text electronic health records and map disorders to SNOMED CT concepts in the UMLS metathesaurus. This paper details our participation to this ShARe/CLEF task. Our approaches are based on using the clinical natural language processing tool Metamap and Conditional Random Fields (CRF) to individuate mentions of disorders and then to map those to SNOMED CT concepts. Empirical results obtained on the 2013 ShARe/CLEF task highlight that our instance of Metamap (after ltering irrelevant semantic types), although achieving a high level of precision, is only able to identify a small amount of disorders (about 21% to 28%) from free-text health records. On the other hand, the addition of the CRF models allows for a much higher recall (57% to 79%) of disorders from free-text, without sensible detriment in precision. When evaluating the accuracy of the mapping of disorders to SNOMED CT concepts in the UMLS, we observe that the mapping obtained by our ltered instance of Metamap delivers state-of-the-art e ectiveness if only spans individuated by our system are considered (`relaxed' accuracy).

The effect of employment while in high school on educational attainment : a conditional difference-in-differences approach

Using American panel data from the National Education Longitudinal Study of 1988, this article investigates the effect of working during grade 12 on attainment.We employ, for the first time in the related literature, a semiparametric propensity score matching approach combined with difference-in-differences. We address selection on both observables and unobservables associated with part-time work decisions, without the need for instrumental variable. Once such factors are controlled for, little to no effects on reading and math scores are found. Overall, our results therefore suggest a negligible academic cost from part-time working by the end of high school.