We prove a new exponential concentration inequality for a plug-in estimator of the Shannon mutual information. Previous results on mutual information estimation only bounded expected error. The advantage of having the...
详细信息
ISBN:
(纸本)9781627480031
We prove a new exponential concentration inequality for a plug-in estimator of the Shannon mutual information. Previous results on mutual information estimation only bounded expected error. The advantage of having the exponential inequality is that, combined with the union bound, we can guarantee accurate estimators of the mutual information for many pairs of random variables simultaneously. As an application, we show how to use such a result to optimally estimate the density function and graph of a distribution which is Markov to a forest graph.
The sample selection is a key in the active learning, because it intends to select the best informative sample which has no label from the pool or online. And then the selected sample needs to be added into the traini...
详细信息
National Information and Communications Technology Australia (NICTA) is the largest ICT research center in Australia, having been established 10 years ago in 2002. It has five laboratories in four Australian capital c...
详细信息
Multi-agent planning is a well-studied problem with various applications including disaster rescue, urban transportation and logistics, both for autonomous agents and for decision support to humans. Due to computation...
Multi-agent planning is a well-studied problem with various applications including disaster rescue, urban transportation and logistics, both for autonomous agents and for decision support to humans. Due to computational constraints, existing research typically focuses on one of two scenarios: unstructured domains with many agents where we are content with heuristic solutions, or domains with small numbers of agents or special structure where we can provide provably near-optimal solutions. By contrast, in this paper, we focus on providing provably near-optimal solutions for domains with large numbers of agents, by exploiting a common domain-general property: if individual agents each have limited influence on the overall solution quality, then we can take advantage of randomization and the resulting statistical concentration to show that each agent can safely plan based only on the average behavior of the other agents. To that end, we make two key contributions: (a) an algorithm, based on Lagrangian relaxation and randomized rounding, for solving multi-agent planning problems represented as large mixed-integer programs, (b) a proof of convergence of our algorithm to a near-optimal solution. We demonstrate the scalability of our approach with a large-scale illustrative theme park crowd management problem.
In this study we show how healthy subjects are able to use a non-invasive Motor Imagery (MI)-based Brain computer Interface (BCI) to achieve linear control of an upper-limb neuromuscular electrical stimulation (NMES) ...
详细信息
In this study we show how healthy subjects are able to use a non-invasive Motor Imagery (MI)-based Brain computer Interface (BCI) to achieve linear control of an upper-limb neuromuscular electrical stimulation (NMES) controlled neuroprosthesis in a simple binary target selection task. Linear BCI control can be achieved if two motor imagery classes can be discriminated with a reliability over 80% in single trial. The results presented in this work show that there was no significant loss of performance using the neuroproshesis in comparison to MI where no stimulation was present. However, it is remarkable how different the experience of the users was in the same experiment. The stimulation either provoked a positive reinforcement feedback, or prevented the user from concentrating in the task.
The administration of hemodialysis (HD) treatment leads to the continuous collection of a vast quantity of medical data. Many variables related to the patient health status, to the treatment, and to dialyzer settings ...
详细信息
ISBN:
(纸本)9781424441198
The administration of hemodialysis (HD) treatment leads to the continuous collection of a vast quantity of medical data. Many variables related to the patient health status, to the treatment, and to dialyzer settings can be recorded and stored at each treatment session. In this study a dataset of 42 variables and 1526 patients extracted from the Fresenius Medical Care database EuCliD was used to develop and apply a random forest predictive model for the prediction of cardiovascular events in the first year of HD treatment. A ridge-lasso logistic regression algorithm was then applied to the subset of variables mostly involved in the prediction model to get insights in the mechanisms underlying the incidence of cardiovascular complications in this high risk population of patients.
Neural batch reinforcement learning (RL) algorithms have recently shown to be a powerful tool for model-free reinforcement learning problems. In this paper, we present a novel learning benchmark from the realm of comp...
详细信息
Optimizing multivariate performance measure is an important task in machinelearning. Joachims (2005) introduced a Support Vector Method whose underlying optimization problem is commonly solved by cutting plane method...
详细信息
Optimizing multivariate performance measure is an important task in machinelearning. Joachims (2005) introduced a Support Vector Method whose underlying optimization problem is commonly solved by cutting plane methods (CPMs) such as SVM-Perf and BMRM. It can be shown that CPMs converge to an ε accurate solution in O(1/λε) iterations, where λ is the trade-off parameter between the regularizer and the loss function. Motivated by the impressive convergence rate of CPM on a number of practical problems, it was conjectured that these rates can be further improved. We disprove this conjecture in this paper by constructing counter examples. However, surprisingly, we further discover that these problems are not inherently hard, and we develop a novel smoothing strategy, which in conjunction with Nesterov's accelerated gradient method, can find an ε accurate solution in O* (min{1/ε, 1/√λε}) iterations. Computationally, our smoothing technique is also particularly advantageous for optimizing multivariate performance scores such as precision/recall break-even point and ROCArea; the cost per iteration remains the same as that of CPMs. Empirical evaluation on some of the largest publicly available data sets shows that our method converges significantly faster than CPMs without sacrificing generalization ability.
We propose two new generalization error bounds for multiple kernel learning (MKL). First, using the bound of Srebro and Ben-David (2006) as a starting point, we derive a new version which uses a simple counting argume...
详细信息
We propose two new generalization error bounds for multiple kernel learning (MKL). First, using the bound of Srebro and Ben-David (2006) as a starting point, we derive a new version which uses a simple counting argument for the choice of kernels in order to generate a tighter bound when 1-norm regularization (sparsity) is imposed in the kernel learning problem. The second bound is a Rademacher complexity bound which is additive in the (logarithmic) kernel complexity and margin term. This dependence is superior to all previously published Rademacher bounds for learning a convex combination of kernels, including the recent bound of Cortes et al. (2010), which exhibits a multiplicative interaction. We illustrate the tightness of our bounds with simulations. Copyright 2011 by the authors.
The AAAI-12 Workshop program was held Sunday and Monday, July 22-23, 2012, at the Sheraton Centre Toronto Hotel in Toronto, Ontario, Canada. The AAAI-12 workshop program included nine workshops covering a wide range o...
详细信息
暂无评论