Learn More
One-Class Collaborative Filtering (OCCF) is an emerging setup in collaborative filtering in which only positive examples or implicit feedback can be observed. Compared with the traditional collaborative filtering setting where the data has ratings, OCCF is more realistic in many scenarios when no ratings are available. In this paper, we propose to improve(More)
We describe a real-time bidding algorithm for performance-based display ad allocation. A central issue in performance display advertising is matching campaigns to ad impressions, which can be formulated as a constrained optimization problem that maximizes revenue subject to constraints such as budget limits and inventory availability. The current practice(More)
Conversations are a useful means of structuring communicative i n teractions among agents. The value of a conversation-based approach is largely determined by the conversational model it uses. Finite State Machines, used heavily to date for this purpose, are not suucient for complex agent interactions requiring a notion of concurrency. We propose the use of(More)
Conversations are a useful means of structuring communicative i n teractions among agents. The value of a conversation-based approach is largely determined by the conversational model it uses. Finite State Machines, used heavily to date for this purpose, are not suucient for complex agent i n ter-actions requiring a notion of concurrency. We propose the use(More)
Power consumption is a critical issue for voice-over-IP (VoIP) over wireless LAN applications, especially when handheld 802.11 voice terminals are used as the end-user device. This paper provides an overview of power save procedures defined in the IEEE 802.11 wireless LAN standard, and proposes a novel power management technique for stations and services(More)
The arachidonic acid derivative, 2-arachidonoyl-glycerol (2-AG), was initially isolated from gut and brain; it is also produced and released from blood and vascular cells. Many of the 2-AG-induced cellular responses (i.e., neuromodulation, cytoprotection and vasodilation) are mediated by cannabinoid receptors CB1 and CB2. The findings presented here(More)
Interacting proteins assemble into molecular machines that control cellular homeostasis in living cells. While the in vitro screening methods have the advantage of providing direct access to the genetic information encoding unknown protein partners, they do not allow direct access to interactions of these protein partners in their natural environment inside(More)
We describe an innovative and scalable recommendation system successfully deployed at eBay. To build recommenders for long-tail marketplaces requires projection of volatile items into a persistent space of latent products. We first present a generative clustering model for collections of unstructured, heterogeneous, and ephemeral item data, under the(More)