Abstract: Various technologies described herein pertain to detecting contextual anomalies in a behavioral network. Label propagation can be performed to construct contexts and assign respective context membership scores to users. Each context can be a respective subset of the users expected to have similar resource usages. The contexts can be constructed and the context membership scores can be assigned by combining behavioral information and contextual side information. The behavioral information can specify respective resource usages by the users within the behavioral network. Moreover, respective contextual anomaly scores for the users can be computed based on the respective context membership scores assigned to the users and the contextual side information. Further, the contextual anomalies can be detected from the contextual anomaly scores.

Abstract: Various technologies described herein pertain to detecting contextual anomalies in a behavioral network. Label propagation can be performed to construct contexts and assign respective context membership scores to users. Each context can be a respective subset of the users expected to have similar resource usages. The contexts can be constructed and the context membership scores can be assigned by combining behavioral information and contextual side information. The behavioral information can specify respective resource usages by the users within the behavioral network. Moreover, respective contextual anomaly scores for the users can be computed based on the respective context membership scores assigned to the users and the contextual side information. Further, the contextual anomalies can be detected from the contextual anomaly scores.

Abstract: Various technologies described herein pertain to detecting contextual anomalies in a behavioral network. Label propagation can be performed to construct contexts and assign respective context membership scores to users. Each context can be a respective subset of the users expected to have similar resource usages. The contexts can be constructed and the context membership scores can be assigned by combining behavioral information and contextual side information. The behavioral information can specify respective resource usages by the users within the behavioral network. Moreover, respective contextual anomaly scores for the users can be computed based on the respective context membership scores assigned to the users and the contextual side information. Further, the contextual anomalies can be detected from the contextual anomaly scores.

Abstract: Real-time query expansion (RTQE) is a process of supplementing an original query with additional terms or expansion choices that are ranked according to some figure of merit and presented while users are still formulating their queries. As disclosed herein, individual terms may be combined and submitted as a phrase into a query. By building the phase term-by-term, users can compositionally formulate queries while maintaining the same benefits that other RTQE interfaces offer. To promote greater flexibility in its working environment, the number of terms that are presented on a display may be reduced. In place of some terms, placeholders may be used and expanded by the user when necessary. This allows phrases to be readily presented on small displays (e.g., hand-held devices).

Abstract: Real-time query expansion (RTQE) is a process of supplementing an original query with addition terms or expansion choices that are ranked according to some figure of merit and presented while users are still formulating their queries. As disclosed herein, phrases may be presented and one or more terms of a focused-on phrase may be pinned (as desirable to the user). Subsequent lists may be presented as a function of pinned terms and/or user input. In one embodiment, a placeholder may be substituted for one or more pinned terms if less than some predetermined threshold of phrases is able to be presented based upon the pinned terms and/or user input, and another list of phrases may be presented as a function of a query using fewer than all the pinned terms. The placeholder may allow out-of-index phrases to be formed, for example, based upon two or more phrases and/or terms input by the user.

Abstract: Various technologies described herein pertain to detecting contextual anomalies in a behavioral network. Label propagation can be performed to construct contexts and assign respective context membership scores to users. Each context can be a respective subset of the users expected to have similar resource usages. The contexts can be constructed and the context membership scores can be assigned by combining behavioral information and contextual side information. The behavioral information can specify respective resource usages by the users within the behavioral network. Moreover, respective contextual anomaly scores for the users can be computed based on the respective context membership scores assigned to the users and the contextual side information. Further, the contextual anomalies can be detected from the contextual anomaly scores.

Abstract: In one embodiment, an event impact signature detector may analyze a time series with external events. A data interface 250 may receive a data set 310 representing the time series with external events. A processor 220 may fit the data set 310 into a baseline time series model 330. The processor 220 may iteratively determine each event location 352 for multiple external events 350 affecting the baseline time series model 330. The processor 220 may iteratively solve for each event impact 354 of the multiple external events 350 factoring in interactions between the multiple external events 350.

Abstract: An augmented large index searching system and method for searching a database of items using a device having a limited input mechanism. Embodiments of the system and method present to a user in an augmented list view or a regular list view a list of items matching a sub-string search. The augmented list view contains a list of sub-group representations so that each sub-group is represented by an item in the sub-group most likely to be selected by the user. The user can select an item wanted by the user or refine the sub-string search by pinning a character to append the character to the sub-string and generate a revised sub-string. The above process is repeated using the revised sub-string. The list can be augmented by displaying visual features that indicate quantity and distinguish between items or characters by using coloring, highlighting, shading, size, and so forth.

Abstract: Described are variational Expectation Maximization (EM) embodiments for learning a mixture model using component-dependent data partitions, where the E-step is sub-linear in sample size while the algorithm still maintains provable convergence guarantees. Component-dependent data partitions into blocks of data items are constructed according to a hierarchical data structure comprised of nodes, where each node corresponds to one of the blocks and stores statistics computed from the data items in the corresponding block. A modified variational EM algorithm computes the mixture model from initial component-dependent data partitions and a variational R-step updates the partitions. This process is repeated until convergence. Component membership probabilities computed in the E-step are constrained such that all data items belonging to a particular block in a particular component-dependent partition behave in the same way.

Abstract: A mode-seeking clustering mechanism identifies clusters within a data set based on the location of individual data point according to modes in a kernel density estimate. For large-scale applications the clustering mechanism may utilize rough hierarchical kernel and data partitions in a computationally efficient manner. A variational approach to the clustering mechanism may take into account variational probabilities, which are restricted in certain ways according to hierarchical kernel and data partition trees, and the mechanism may store certain statistics within these trees in order to compute the variational probabilities in a computational efficient way. The clustering mechanism may use a two-step variational expectation and maximization algorithm and generalizations hereof, where the maximization step may be performed in different ways in order to accommodate different mode-seeking algorithms, such as the mean shift, mediod shift, and quick shift algorithms.

Abstract: Real-time query expansion (RTQE) is a process of supplementing an original query with additional terms or expansion choices that are ranked according to some figure of merit and presented while users are still formulating their queries. Individual terms may be combined and submitted as a phrase into a query. By building the phase term-by-term, users can compositionally formulate queries while maintaining the same benefits that other RTQE interfaces offer. The benefits include, reducing the number of keystrokes and improving retrieval performance. To promote greater flexibility in its working environment, the number of terms that are presented on a display may be reduced. In place of some terms, placeholders may be used and expanded by the user when necessary. This allows phrases to be readily presented on small displays (e.g., hand-held devices).

Abstract: In one embodiment, an event impact signature detector may analyze a time series with external events. A data interface 250 may receive a data set 310 representing the time series with external events. A processor 220 may fit the data set 310 into a baseline time series model 330. The processor 220 may iteratively determine each event location 352 for multiple external events 350 affecting the baseline time series model 330. The processor 220 may iteratively solve for each event impact 354 of the multiple external events 350 factoring in interactions between the multiple external events 350.

Abstract: Real-time query expansion (RTQE) is a process of supplementing an original query with addition terms or expansion choices that are ranked according to some figure of merit and presented while users are still formulating their queries. As disclosed herein, phrases may be presented and one or more terms of a focused-on phrase may be pinned (as desirable to the user). Subsequent lists may be presented as a function of pinned terms and/or user input. In one embodiment, a placeholder may be substituted for one or more pinned terms if less than some predetermined threshold of phrases is able to be presented based upon the pinned terms and/or user input, and another list of phrases may be presented as a function of a query using fewer than all the pinned terms. The placeholder may allow out-of-index phrases to be formed, for example, based upon two or more phrases and/or terms input by the user.

Abstract: A mode-seeking clustering mechanism identifies clusters within a data set based on the location of individual data point according to modes in a kernel density estimate. For large-scale applications the clustering mechanism may utilize rough hierarchical kernel and data partitions in a computationally efficient manner. A variational approach to the clustering mechanism may take into account variational probabilities, which are restricted in certain ways according to hierarchical kernel and data partition trees, and the mechanism may store certain statistics within these trees in order to compute the variational probabilities in a computational efficient way. The clustering mechanism may use a two-step variational expectation and maximization algorithm and generalizations hereof, where the maximization step may be performed in different ways in order to accommodate different mode-seeking algorithms, such as the mean shift, mediod shift, and quick shift algorithms.

Abstract: A multi-modal search system (and corresponding methodology) that employs wildcards is provided. Wildcards can be employed in the search query either initiated by the user or inferred by the system. These wildcards can represent uncertainty conveyed by a user in a multi-modal search query input. In examples, the words “something” or “whatchamacallit” can be used to convey uncertainty and partial knowledge about portions of the query and to dynamically trigger wildcard generation.

Abstract: Described are variational Expectation Maximization (EM) embodiments for learning a mixture model using component-dependent data partitions, where the E-step is sub-linear in sample size while the algorithm still maintains provable convergence guarantees. Component-dependent data partitions into blocks of data items are constructed according to a hierarchical data structure comprised of nodes, where each node corresponds to one of the blocks and stores statistics computed from the data items in the corresponding block. A modified variational EM algorithm computes the mixture model from initial component-dependent data partitions and a variational R-step updates the partitions. This process is repeated until convergence. Component membership probabilities computed in the E-step are constrained such that all data items belonging to a particular block in a particular component-dependent partition behave in the same way.

Abstract: Systems and methods are provided for parsimonious representation of large sets of multi-resolution value-item lists. A hierarchical data structure associated with the lists and conditioning variables is learnt while exploiting both semantics encoded in target variables and a notion of nearness among nodes at the same detail level in the hierarchical data structure. Such a level of description can be dictated by a depth in a tree data structure. A compression scheme that relies on (i) a similarity metric and (ii) recursive greedy pairing of value-item lists in order to promote elements populating a specific tree node upwards in the tree facilitates a parsimonious representation of the compressed hierarchic structure.

Abstract: Systems and methods that create a classification of sentences in a language, and further construct associated local versions of language models, based on geographical location and/or other demographic criteria—wherein such local language models can be of different levels of granularity according to chosen demographic criteria. The subject innovation employs a classification encoder component that forms a classification (e.g. a tree structure) of sentences, and a local language models encoder component, which employs the classification of sentences in order to construct the localized language models. A decoder component can subsequently enable local word wheeling and/or local web search by blending k-best answers from local language models of varying demographic granularity that match users demographics. Hence, k-best matches for input data by users in one demographic locality can be different from k-best matches for the same input by other users in another locality.

Abstract: The claimed subject matter provides systems and/or methods that expand input data. An interface can obtain input data and a wildcard insertion component can modify the input data to include at least one implicit wildcard inserted at an end of each intended word. Additionally, an expansion component can generate a candidate list of expanded data based at least in part on the input data including the at least one implicit wildcard utilizing a language model that provides likely expansions of wildcards. Further, the expansion component can evaluate the input data at a server side.

Abstract: An augmented large index searching system and method for searching a database of items using a device having a limited input mechanism. Embodiments of the system and method present to a user in an augmented list view or a regular list view a list of items matching a sub-string search. The augmented list view contains a list of sub-group representations so that each sub-group is represented by an item in the sub-group most likely to be selected by the user. The user can select an item wanted by the user or refine the sub-string search by pinning a character to append the character to the sub-string and generated a revised sub-string. The above process is repeated using the revised sub-string. The list can be augmented by displaying visual features that indicate quantity and distinguish between items or characters by using coloring, highlighting, shading, size, and so forth.