Rahul Urgaonkar wins IEEE Communications Society William R. Bennett Prize
Rahul Urgaonkar, a senior applied scientist with Amazon Advertising, and his co-authors Kevin Spiteri and Ramesh K. Sitaraman, were selected for the IEEE Communications Society William R. Bennett Prize earlier this year.
The authors were honored for the 2020 paper, “BOLA: Near-Optimal Bitrate Adaptation for Online Videos”, during the annual IEEE International Conference on Communications (ICC) in May in Rome. The award recognizes the publication of an original paper published in the IEEE/ACM Transactions on Networking or the IEEE Transactions on Network and Service Management in the previous three years
Urgaonkar, who contributed to the paper in his former role as a senior research scientist with Prime Video, noted BOLA is an acronym for Buffer Occupancy based Lyapunov Algorithm. “It’s a new algorithm for adaptive bitrate streaming (ABR), which refers to the set of techniques used by modern video players to optimize the playback performance of videos streamed online,” he explained.
BOLA offers significant improvements in streaming performance across a range of metrics such as frequency of re-buffers/pauses during playback or the quality of videos shown.
“These metrics directly impact customer experience with Prime Video and optimizing them is important to maximize user engagement and satisfaction with the service. From a research perspective, BOLA was the first ABR algorithm that used a mathematical utility maximization framework to provide theoretically rigorous performance guarantees. It has since become a highly cited paper and is regularly used by other researchers in benchmarking their algorithms.
Urgaonkar, who now works with the Amazon Demand Side Platform team, said he was thrilled to win the award. “It is a recognition of the impact of this work, both in terms of advancing the state-of-the-art and its practical utility. It was also an opportunity to showcase the amazing work being done at Amazon Prime Video to the broader research community.”
Yizhou Sun receives multiple honors
Yizhou Sun, an Amazon Scholar and associate professor of computer science at the University of California, Los Angeles (UCLA) recently received multiple honors. Sun works a Scholar in Amazon Ads where she is constructing a heterogeneous information network based on Amazon Ads data.
She was named on the IEEE Intelligent System’s “AI’s 10 to Watch” list in March. Sun was cited as “pioneer in heterogeneous information network (HIN) mining, with a recent focus on deep graph learning, neural symbolic reasoning, and providing neural solutions to multiagent dynamical systems. Her work has a wide spectrum of applications, ranging from e-commerce, health care, and material science to hardware design.”
Earlier this year, Sun also received the SIAM International Conference on Data Mining (SDM23) Early Career Data Mining Research Award. That award recognizes “one who has made outstanding, influential, and lasting contributions in the field of data analysis” within 10 years of receiving their PhD. Sun earned her PhD in computer science from the University of Illinois at Urbana-Champaign in 2012.
Finally, Sun and her co-authors won the The Web Conference Best Student Paper Award — meaning it was a top 2 paper among 1,8000 submissions — at the ACM Web Conference in May for their paper, "A Single Vector Is Not Enough: Taxonomy Expansion via Box Embeddings".
Sun is also a two-time recipient of an Amazon Research Award. She won her 2018 award from Amazon’s Product Graph Team and her 2020 award from the Deep Graph Learning Team.
Pooyan Amir-Ahmadi wins 2023 QE Best Paper Prize
Pooyan Amir-Ahmadi, a senior economist on the Supply Chain Optimization Technologies (SCOT) team, and his co-author Thorsten Drautzburg received the 2023 Quantitative Economics Best Paper Prize Awarded from the Econometric Society. The authors were honored for their 2021 paper, “Identification and Inference with Ranking Restrictions".
The Econometric Society is “an international society for the advancement of economic theory in its relation to statistics and mathematics.” The prize alternates yearly between Quantitative Economics (where the award-winning paper was published in 2021) and Theoretical Economics. The single paper winner is selected from all papers published in the corresponding journal during the previous two years by an external committee.
Alexandros Potamianos elevated to ISCA fellow
Alexandros Potamianos, an Amazon Scholar and adjunct associate professor of electrical and computer engineering at the University of Southern California (USC) was named as a fellow of the International Speech Communication Association (ISCA).
Potamianos, who works as a Scholar with Amazon’s Alexa Natural Understanding team, was honored “for contributions to human-centered speech and multimodal signal analysis and conversational technologies”. He will be recognized at Interspeech 2023 in Dublin, Ireland, in August.
Alexandre Belloni receives Bank of America Faculty Award
Alexandre Belloni, an Amazon Scholar and the Westgate Distinguished Professor of Decision Sciences in the Fuqua School of Business at Duke University, received the 2022 Bank of America Faculty Award in April.
The Bank of America Award is Fuqua’s highest faculty honor and is given for outstanding contributions to the school in terms of teaching performance, research performance, leadership, and service to Fuqua, Duke University, and outside Duke.
Belloni, who joined Amazon as a Scholar in 2018, studies problems related to mechanism design and machine learning at Fulfillment by Amazon (FBA), the subdivision of Amazon’s Supply Chain Optimization Technologies (SCOT) organization for third-party sellers who use Amazon’s storage and fulfillment capabilities.
