Amazon.com

About: Amazon.com is a company organization based out in Seattle, Washington, United States. It is known for research contribution in the topics: Computer science & Service (business). The organization has 13363 authors who have published 17317 publications receiving 266589 citations.

System-wide query optimization

Abstract: A locally optimized plan for executing a command using a sequence of steps can be determined for a single computing node. However, the locally optimized sequence of steps may not be optimized for a combined system comprising multiple computing nodes, any one of which may be tasked with executing the command. A plan that is optimized for the combined system may be determined by comparing the predicted cost of locally optimized plans for computing nodes in the combined system.

Attack traffic signature generation using statistical pattern recognition

Abstract: A pattern recognition security system (“PRSS”) generates a packet signature from network traffic, including attack packets. The PRSS can utilize a statistical pattern recognition based approach to generate attack traffic signatures, such as for DDoS or DoS attacks. In some embodiments, the PRSS dynamically creates training sets from actual captured data, allowing the PRSS to adapt to changes in network attacks. For example, more sophisticated DDoS attacks commonly rotate through different attacking computers to vary the packet attributes of attack packets sent to a target system. However, as the PRSS can determine packet signatures based on the actual captured data packets, the PRSS can adapt to the changes in the attack. In some embodiments, the PRSS may determine packet signatures in real-time or near real time during an attack, allowing the PRSS to quickly react to changes in attack traffic.

Secure tunnel infrastructure between hosts in a hybrid network environment

Abstract: Technologies are described herein for establishing a secure tunnel infrastructure between host computers in a hybrid network environment. A first network tunnel is established between a border device in a first network and a border device in a second network. A second network tunnel is established between a first host computer in the first network and the border device in the first network. Similarly, a third network tunnel is established between the border device in the second network and a second host computer in the second network. The networking infrastructures of the first and second networks are then configured so that network packets from the first host computer arriving at the border device in the first network through the second network tunnel are sent through the first network tunnel to the border device in the second network, and then through the third network tunnel to the second host computer.

Neural Cross-Lingual Entity Linking

Abstract: A major challenge in Entity Linking (EL) is making effective use of contextual information to disambiguate mentions to Wikipedia that might refer to different entities in different contexts. The problem exacerbates with cross-lingual EL which involves linking mentions written in non-English documents to entries in the English Wikipedia: to compare textual clues across languages we need to compute similarity between textual fragments across languages. In this paper, we propose a neural EL model that trains fine-grained similarities and dissimilarities between the query and candidate document from multiple perspectives, combined with convolution and tensor networks. Further, we show that this English-trained system can be applied, in zero-shot learning, to other languages by making surprisingly effective use of multi-lingual embeddings. The proposed system has strong empirical evidence yielding state-of-the-art results in English as well as cross-lingual: Spanish and Chinese TAC 2015 datasets.

BOLA: Near-Optimal Bitrate Adaptation for Online Videos

Abstract: Modern video players employ complex algorithms to adapt the bitrate of the video that is shown to the user. Bitrate adaptation requires a tradeoff between reducing the probability that the video freezes (rebuffers) and enhancing the quality of the video. A bitrate that is too high leads to frequent rebuffering, while a bitrate that is too low leads to poor video quality. Video providers segment videos into short segments and encode each segment at multiple bitrates. The video player adaptively chooses the bitrate of each segment to download, possibly choosing different bitrates for successive segments. We formulate bitrate adaptation as a utility-maximization problem and devise an online control algorithm called BOLA that uses Lyapunov optimization to minimize rebuffering and maximize video quality. We prove that BOLA achieves a time-average utility that is within an additive term $O(1/V)$ of the optimal value, for a control parameter V related to the video buffer size. Further, unlike prior work, BOLA does not require prediction of available network bandwidth. We empirically validate BOLA in a simulated network environment using a collection of network traces. We show that BOLA achieves near-optimal utility and in many cases significantly higher utility than current state-of-the-art algorithms. Our work has immediate impact on real-world video players and for the evolving DASH standard for video transmission. We also implemented an updated version of BOLA that is now part of the standard reference player dash.js and is used in production by several video providers such as Akamai, BBC, CBS, and Orange.