Abstract: A method and system are disclosed for learning a demand model and simulation parameters from validation information. Validation information is received from automatic fare collection systems and trips are reconstructed from the validation information. Origins, destinations, and arrival/departure times are estimated from the reconstructed trips. A demand model is then generated from the origins, destinations, and times. Assignment model parameters are then learned from the received validation information and demand model via iterative simulations. Infrastructure changes are made to a simulated transportation network based on the assignment and demand model using the learned parameters. A simulated response of the transportation network to the infrastructure change is then output.

Abstract: A method for link prediction includes providing training samples for at least one relation. The training samples include positive training samples in which a first of a set of entities is a subject in the relation and a second of the set of entities is an object in the relation. An input matrix is generated for each of the at least one relation, based on the training samples. Parameters of a scoring function which minimize an error between a reconstructed matrix and the input matrix are learned, the parameters including a set of latent factors for each entity, each of the latent factors being a complex number. The parameters of the scoring function may be output for performing link prediction and/or used for predicting an entity for a relation from a part of the reconstructed matrix.

Abstract: A penalized loss is optimized using a corpus of language samples respective to a set of parameters of a language model. The penalized loss includes a function measuring predictive accuracy of the language model respective to the corpus of language samples and a penalty comprising a tree-structured norm. The trained language model with optimized values for the parameters generated by the optimizing is applied to predict a symbol following sequence of symbols of the language modeled by the language model. In some embodiments the penalty comprises a tree-structured lp-norm, such as a tree-structured l2-norm or a tree-structured l?-norm. In some embodiments a tree-structured l?-norm operates on a collapsed suffix trie in which any series of suffixes of increasing lengths which are always observed in the same context are collapsed into a single node. The optimizing may be performed using a proximal step algorithm.

Abstract: A method for mobility demand modeling uses passenger demand data and geographical data for a transportation network. The demand data includes, for each of a plurality of stops in the transportation network, a passenger demand for each of a plurality of time intervals. The geographical data includes, for each of the plurality of stops in the transportation network, geographical features representing local points-of-interest. A dependence between the demand data and the geographical data is modeled by learning first and second mapping functions for embedding the demand data and the geographical data into the same latent space. The first and second mapping functions are learnt so as to optimize a correlation between the passenger demand data and the geographic data in the latent space. From the model, a prediction of passenger demand or of local point of interest for a proposed stop in the transport network can be generated.

Abstract: A method and system are disclosed for learning a demand model and simulation parameters from validation information. Validation information is received from automatic fare collection systems and trips are reconstructed from the validation information. Origins, destinations, and arrival/departure times are estimated from the reconstructed trips. A demand model is then generated from the origins, destinations, and times. Assignment model parameters are then learned from the received validation information and demand model via iterative simulations. Infrastructure changes are made to a simulated transportation network based on the assignment and demand model using the learned parameters. A simulated response of the transportation network to the infrastructure change is then output.

Abstract: A penalized loss is optimized using a corpus of language samples respective to a set of parameters of a language model. The penalized loss includes a function measuring predictive accuracy of the language model respective to the corpus of language samples and a penalty comprising a tree-structured norm. The trained language model with optimized values for the parameters generated by the optimizing is applied to predict a symbol following sequence of symbols of the language modeled by the language model. In some embodiments the penalty comprises a tree-structured lp-norm, such as a tree-structured l2-norm or a tree-structured l?-norm. In some embodiments a tree-structured l?-norm operates on a collapsed suffix trie in which any series of suffixes of increasing lengths which are always observed in the same context are collapsed into a single node. The optimizing may be performed using a proximal step algorithm.

Abstract: Given the integral Z:=ƒ(t)g(t)dv(t) of the product of two functions ƒ and g defined on a space , a pivot function r:+ is optimized to minimize the bound defined by the inequality ? Z ? ( ? ? ? f ? ( t ) p ? r ? ( t ) p ? ? v ? ( t ) ) 1 p ? ( ? ? ? g ? ( t ) q ? r ? ( t ) - q ? ? v ? ( t ) ) 1 q where v is a measure on the space , p?1 and 1 p + 1 q = 1 to determine an optimized pivot function ropt(t). The product ƒg may be evaluated as ƒg=ƒproptp or ƒg=gqropt?q. The integral Z:=ƒ(t)g(t)dv(t) may e evaluated as the product ( ? ? ? f ? ( t ) p ? r ? ( t ) p ? ? v ? ( t ) ) 1 p ? ( ? ? ? g ? ( t ) q ? r ? ( t ) - q ? ? v ? ( t ) ) 1 q with r(t)=ropt(t). The method is suitably performed by an electronic data processing device.

Abstract: A method for performing data processing through a pipeline of components includes receiving a set of training observations, each including partial user feedback relating to error in data output by the pipeline for respective input data. Some pipeline components commit errors for at least some of the input data, contributing to an error in the respective output data. A prediction model models a probability of a pipeline component committing an error, given input data. Model parameters are learned using the training observations. For a new observation which includes input data and, optionally, partial user feedback indicating that an error has occurred in processing the new input data, without specifying which pipeline component(s) contributed to the observed error in the output data, a prediction is made as to which of the pipeline components contributed to the error in the output (if any).

Abstract: A control system reduces energy consumption in a multi-device system comprising a plurality of devices. The control system includes at least one processor. The processor is programmed to receive a job to be executed, as well as a selection of one of the plurality of devices for executing the job and a transfer cost for transferring the job from the selected device to each of the plurality of devices. A device to execute the job is determined through optimization of a first cost function. The first cost function is based on the device selection and the transfer costs. The job is assigned to the determined device and a time-out for each device in the multi-device system is determined through optimization of a second cost function. The second cost function is based on an expected energy consumption by the multi-device system. The devices are provided with the determined time-outs.

Abstract: A method and system are disclosed for estimating origin and destination locations of users of a transportation system. The origins and destinations of known users are determined during a segment of an analysis period from validation information for all users of the transportation system. The origins and destinations are then mapped to probable locations associated with the transportation network. A destination probability is then computed for each destination location of an individual origin location. A unknown users are then apportioned to each destination, which may be based on the number of unknown users on a vehicle traveling from the origin to the destination, the computed probability, and the validation information, so as to estimate the number of users traveling from an origin location to any corresponding destination location on the transportation system.

Abstract: A method for performing data processing through a pipeline of components includes receiving a set of training observations, each including partial user feedback relating to error in data output by the pipeline for respective input data. Some pipeline components commit errors for at least some of the input data, contributing to an error in the respective output data. A prediction model models a probability of a pipeline component committing an error, given input data. Model parameters are learned using the training observations. For a new observation which includes input data and, optionally, partial user feedback indicating that an error has occurred in processing the new input data, without specifying which pipeline component(s) contributed to the observed error in the output data, a prediction is made as to which of the pipeline components contributed to the error in the output (if any).

Abstract: A computer-implemented method for identifying constraints to reducing consumable usage includes acquiring print job information for a set of print jobs submitted for printing by a set of users. A print job representation is computed for each of the print jobs based on features extracted from the print job information. Provision is made for user-annotation of the submitted print jobs with a task category and a constraint category. Each of a plurality of task categories represents a respective task with which the printing of a print job is associated. Each of a plurality of selectable constraint categories expresses a different reason for printing the print job. User-annotations are received for at least some of the submitted print jobs. The print jobs are clustered into clusters based on the print job representations and task category annotations.

Abstract: A convex regularized loss function is minimized respective to a prediction tensor of order K to generate an optimized prediction tensor of order K where K>2. The convex regularized loss function comprises a linear combination of (i) a loss function comparing the prediction tensor and an observation tensor of order K representing a set of observations and (ii) a regularization parameter including a K-th order matrix norm decomposition of the tensor trace norm of the prediction tensor. In some such embodiments, the observation tensor of order K represents a set of social network observations and includes at least dimensions corresponding to (1) users, (2) items, and (3) tags. The optimized prediction tensor of order K is suitably used to perform inference operations.

Abstract: Iterative rejection sampling is performed on a domain in accordance with a target distribution. The domain is partitioned to define a partition comprising partition elements, and each iteration of the rejection sampling includes selecting a partition element from the partition in accordance with partition element selection probabilities. A sample of the domain is acquired in the selected partition element according to a normalized proposal distribution that is associated with and normalized over the selected partition element. The acquired sample is accepted or rejected based on the target distribution and a bound associated with the selected partition element. During the iterative rejection sampling, the partition is adapted by replacing a partition element of the partition with two or more split partition elements, associating bounds with the split partition elements, and computing partition element selection probabilities for the split partition elements.

Abstract: A computer-implemented method for identifying constraints to reducing consumable usage includes acquiring print job information for a set of print jobs submitted for printing by a set of users. A print job representation is computed for each of the print jobs based on features extracted from the print job information. Provision is made for user-annotation of the submitted print jobs with a task category and a constraint category. Each of a plurality of task categories represents a respective task with which the printing of a print job is associated. Each of a plurality of selectable constraint categories expresses a different reason for printing the print job. User-annotations are received for at least some of the submitted print jobs. The print jobs are clustered into clusters based on the print job representations and task category annotations.

Abstract: A method and system are disclosed for automatically tagging locations using collected traveler information. Traveler information, including a time/date stamp and a unique identification associated with the traveler are collected and stored in a database with locations corresponding to transportation stops. A location query, which includes a location type, an analysis period, optionally, an analysis approach, and a user selected threshold are received and a number of time/location stamps for each location is determined based upon an interval associated with the selected type. The maximum number of time/location stamps for that location is determined, and using the selected threshold, a minimum number of stamps required to designate a location as the selected type is determined. When the number of time/location stamps within the time interval for the selected type is greater than or equal to the minimum number calculated, the location is tagged as the selected location type.

Abstract: A convex regularized loss function is minimized respective to a prediction tensor of order K to generate an optimized prediction tensor of order K where K>2. The convex regularized loss function comprises a linear combination of (i) a loss function comparing the prediction tensor and an observation tensor of order K representing a set of observations and (ii) a regularization parameter including a K-th order matrix norm decomposition of the tensor trace norm of the prediction tensor. In some such embodiments, the observation tensor of order K represents a set of social network observations and includes at least dimensions corresponding to (1) users, (2) items, and (3) tags. The optimized prediction tensor of order K is suitably used to perform inference operations.

Abstract: A method and system are disclosed for estimating origin and destination locations of users of a transportation system. The origins and destinations of known users are determined during a segment of an analysis period from validation information for all users of the transportation system. The origins and destinations are then mapped to probable locations associated with the transportation network. A destination probability is then computed for each destination location of an individual origin location. A unknown users are then apportioned to each destination, which may be based on the number of unknown users on a vehicle traveling from the origin to the destination, the computed probability, and the validation information, so as to estimate the number of users traveling from an origin location to any corresponding destination location on the transportation system.

Abstract: A method and system for managing distribution lists rely on the collection of job log data from shared devices, such as networked printers. For each printer, a usage community comprising users of the shared device, can be determined, based at least in part on the job log data. At least one distribution list of users is generated, based on the usage community. The distribution list can be linked with a mailer program, whereby users in the usage community are grouped together under a common contact address. Updating the distribution list at intervals to reflect changes in the usage community allows a static email address to be used for a varying group of users.

Abstract: In an inference system for organizing a corpus of objects, feature representations are generated comprising distributions over a set of features corresponding to the objects. A topic model defining a set of topics is inferred by performing latent Dirichlet allocation (LDA) with an Indian Buffet Process (IBP) compound Dirichlet prior probability distribution. The inference is performed using a collapsed Gibbs sampling algorithm by iteratively sampling (1) topic allocation variables of the LDA and (2) binary activation variables of the IBP compound Dirichlet prior. In some embodiments the inference is configured such that each inferred topic model is a clean topic model with topics defined as distributions over sub-sets of the set of features selected by the prior. In some embodiments the inference is configured such that the inferred topic model associates a focused sub-set of the set of topics to each object of the training corpus.