- talks - lists.cs.princeton.edu

Mingzhe Wang will present his General Exam "Structured Matching for Phrase Localization" on Monday, February 3, 2020 at 3pm in CS 302
by Nicki Mahler 24 Jan '20

24 Jan '20

Mingzhe Wang will present his General Exam on Monday, February 3, 2020 at 3pm in CS 302. The members of his committee are as follows : Jia Deng (adviser), Olga Russakovsky, and Danqi Chen. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. In this paper we introduce a new approach to phrase localization: grounding phrases in sentences to image regions. We propose a structured matching of phrases and regions that encourages the semantic relations between phrases to agree with the visual relations between regions. We formulate structured matching as a discrete optimization problem and relax it to a linear program. We use neural networks to embed regions and phrases into vectors, which then define the similarities (matching weights) between regions and phrases. We integrate structured matching with neural networks to enable end-to-end training. Experiments on Flickr30K Entities demonstrate the empirical effectiveness of our approach. Textbook: Szeliski, R., 2010. Computer vision: algorithms and applications. Springer Science & Business Media. Papers: Kulkarni, G., Premraj, V., Dhar, S., Li, S., Choi, Y., Berg, A.C. and Berg, T.L., 2011. Baby talk: Understanding and generating image descriptions. In Proceedings of the 24th CVPR. Plummer, B.A., Wang, L., Cervantes, C.M., Caicedo, J.C., Hockenmaier, J. and Lazebnik, S., 2015. Flickr30k entities: Collecting region-to-phrase correspondences for richer image-to-sentence models. In Proceedings of the IEEE international conference on computer vision (pp. 2641-2649). Wang, L., Li, Y. and Lazebnik, S., 2016. Learning deep structure-preserving image-text embeddings. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5005-5013). Rohrbach, A., Rohrbach, M., Hu, R., Darrell, T. and Schiele, B., 2016, October. Grounding of textual phrases in images by reconstruction. In European Conference on Computer Vision (pp. 817-834). Springer, Cham. Karpathy, A., Joulin, A. and Fei-Fei, L.F., 2014. Deep fragment embeddings for bidirectional image sentence mapping. In Advances in neural information processing systems (pp. 1889-1897). Karpathy, A. and Fei-Fei, L., 2015. Deep visual-semantic alignments for generating image descriptions. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3128-3137). Hu, R., Xu, H., Rohrbach, M., Feng, J., Saenko, K. and Darrell, T., 2016. Natural language object retrieval. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 4555-4564). Klein, B., Lev, G., Sadeh, G. and Wolf, L., 2014. Fisher vectors derived from hybrid gaussian-laplacian mixture models for image annotation. arXiv preprint arXiv:1411.7399. Vinyals, O., Toshev, A., Bengio, S. and Erhan, D., 2015. Show and tell: A neural image caption generator. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3156-3164). Fukui, A., Park, D.H., Yang, D., Rohrbach, A., Darrell, T. and Rohrbach, M., 2016. Multimodal compact bilinear pooling for visual question answering and visual grounding. arXiv preprint arXiv:1606.01847.

1 0

Ariel Schvartzman will present his Pre FPO "Circumventing Lower Bounds in Mechanism and Tournament Design" on Monday, January 27, 2020 in CS at 3pm in CS 302
by Nicki Mahler 21 Jan '20

21 Jan '20

Ariel Schvartzman will present his Pre FPO "Circumventing Lower Bounds in Mechanism and Tournament Design" on Monday, January 27, 2020 in CS at 3pm in CS 302. The members of his committee are: Matt Weinberg (adviser/reader), Mark Braverman (reader), Gillat Kol (examiner), Ran Raz (examiner) and Elad Hazan (examiner). Everyone is invited to attend his talk. The talk title and abstract follow below: Title: Circumventing Lower Bounds in Mechanism and Tournament Design How should a seller price multiple items in order to maximize their revenue from a single buyer? This question has been key in connecting research done by computer scientists and economists to applications such as online ad auctions and spectrum auctions. It was shown almost 40 years ago that if the buyer only cares for one item it is optimal for the seller to offer the buyer the item at a take-it-or-leave-it price. This elegant solution, however, may be far from optimal even for the case with a single buyer interested in just two items. Optimal auction design for two or more items is intricate for a number of reasons: the auctions may be bizarre, computationally hard to find or simply too complex to present to a bidder. Numerous results suggest that (under reasonable complexity assumptions) efficiently finding optimal auctions, even in some simple settings, is impossible. In my talk, I will present numerous ways in which we try to circumvent these impossibility results in order to recover positive results. These include the study of different multi-item models and beyond-worst case analysis for mechanism design. I will also discuss recent advances in tournament design, a field at the intersection of mechanism design and social choice theory. For problems in this field we get around known impossibility results via approximations in order to find approximately strategy-proof tournament rules.

1 0

Claudia Roberts will present her General Exam "Selectively Contextual Bandits" on Thursday, January 23, 2020 at 2pm in CS 402
by Nicki Mahler 16 Jan '20

16 Jan '20

Claudia Roberts will present her General Exam "Selectively Contextual Bandits" on Thursday, January 23, 2020 at 2pm in CS 402. The members of her committee are as follows: Arvind Narayanan (adviser), Matthew Salganik (SOC), and Barbara Engelhardt Everyone is invited to attend her talk, and those faculty wishing to remain for the oral exam following are welcome to do so. Her abstract and reading list follow below. Personalization is an integral part of most web-service applications and determines which experience to display to each member. A popular algorithmic framework used in industrial personalization systems are contextual bandits, which seek to learn a personalized treatment assignment policy in the presence of treatment effects that vary with the observed contextual features of the members. In order to keep the optimization task tractable, such systems can myopically make independent personalization decisions that can conspire to create a suboptimal experience in the aggregate of the member’s interaction with the web-service. We design a new family of online learning algorithms that benefit from personalization while optimizing the aggregate impact of the many independent decisions. Our approach selectively interpolates between any contextual bandit algorithm and any context-free multi-armed bandit algorithm and leverages the contextual information for a treatment decision only if this information promises significant gains over a decision that does not take it into account. Apart from helping users of personalization systems feel less targeted, simplifying the treatment assignment policy by making it selectively reliant on the context can help improve the rate of learning. We evaluate our approach on several datasets including a video subscription web-service and show the benefits of such a hybrid policy. Reading List : Methods/Techniques (Contextual Bandits) * [ https://papers.nips.cc/paper/4321-an-empirical-evaluation-of-thompson-sampl… | An Empirical Evaluation of Thompson Sampling ] * [ https://arxiv.org/pdf/1003.0146.pdf | A Contextual-Bandit Approach to Personalized News Article Recommendation ] * [ https://web.stanford.edu/~bvr/pubs/TS_Tutorial.pdf | A Tutorial on Thompson Sampling ] * [ https://arxiv.org/pdf/1003.5956 | Unbiased Offline Evaluation of Contextual-bandit-based News Article Recommendation Algorithms ] * [ https://www.microsoft.com/en-us/research/wp-content/uploads/2016/06/ftir-on… | Online Evaluation for Information Retrieval ] Textbooks * [ http://incompleteideas.net/book/the-book-2nd.html | Reinforcement Learning: An Introduction ] (Ch 2, 16.7) * [ http://www.mmds.org/#ver21 | Mining of Massive Datasets ] (Ch 8, 9) * [ http://shop.oreilly.com/product/0636920027393.do | Bandit Algorithms for Website Optimization ] Historical Context * [ http://rr.cs.cmu.edu/aaai.pdf | Foundations and Grand Challenges of Artificial Intelligence ] Motivating * [ https://link.springer.com/content/pdf/10.1023%2FA%3A1007046204478.pdf | The Perpetuation of Subtle Prejudice: Race and Gender Imagery in 1990s Television Advertising ] * [ https://www.researchgate.net/publication/5153026_Getting_too_personal_React… | Getting too personal: Reactance to highly personalized email solicitations ] * [ https://science.sciencemag.org/content/sci/347/6221/509.full.pdf | Privacy and human behavior in the age of information ] * [ https://www.sciencedirect.com/science/article/pii/S0167923610001983 | The personalization privacy paradox: An exploratory study of decision making process for location-aware marketing ] * [ https://www.microsoft.com/en-us/research/uploads/prod/2019/07/mehrotra-2017… | Auditing Search Engines for Differential Satisfaction Across Demographics ]

1 0

Hansen Zhang will present his Pre FPO "Practical High Performance Containment on FPGA" on Wednesday, January 15, 2020 at 2pm in CS 301
by Nicki Mahler 14 Jan '20

14 Jan '20

Hansen Zhang will present his Pre FPO " Practical High Performance Containment on FPGA" on Wednesday, January 15, 2020 at 2pm in CS 301. The members of his committee are as follows: David August (Reader and Examiner), Adrian Caulfield (Microsoft- Reader), Sharad Malik (Examiner), and Andrew Appel (Examiner) Everyone is invited to his talk. The talk title and abstract follows below. Title: Practical High Performance Containment on FPGA Abstract: The security of a computer system ultimately rests on the security of the underlying hardware components. A containment-based security architecture secures systems using a single, simple HW root of trust to contain the malicious effects of untrusted components within the system. However, prior containment-based security architecture implementations have suffered from either unreasonable adoption costs or significant performance slowdowns. In this talk, I will present FPGAGuard, the first containment-based security architecture implementation that is both efficient and practical. FPGAGuard secures a commercial off-the-shelf (COTS) computer system with a commodity PCIe FPGA network card as the root of trust and demonstrates reasonable performance on real programs.

1 1

Jeffrey Helt will present his General Exam "FDR: Addressing the Parallelism Gap in Primary-backup Databases" on Tuesday, January 21, 2020 at 1pm in CS 402.
by Nicki Mahler 14 Jan '20

14 Jan '20

Jeffrey Helt will present his General Exam "FDR: Addressing the Parallelism Gap in Primary-backup Databases" on Tuesday, January 21, 2020 at 1pm in CS 402. The members of his committee are as follows: Wyatt Lloyd (adviser), Michael Freedman and Amit Levy. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. Asynchronously replicated primary-backup databases are the beating heart of many large applications. The backups provide availability if the primary fails and may serve read-only transactions to increase throughput for all clients and reduce latency for clients in other geographic regions. However, to retain the correctness of overlying applications despite their read-only transaction returning stale values, backups should appear virtually indistinguishable from the primary. Thus, backups must guarantee monotonic prefix consistency, where they present a progressing sequence of the primary's recent states. But monotonic prefix consistency severely constrains a backup's execution because it must exactly copy (or clone) the commit order resulting from the primary's concurrency control. Existing cloned concurrency control protocols guarantee this order by limiting the backup's parallelism, but as a result, a parallelism gap exists between them and the primary. In this paper, we prove this parallelism gap leads to unbounded replication lag, where changes committed by the primary may take infinitely long to propagate to the backup, for some workloads. Unbounded lag recently caused catastrophic failures (i.e., user data loss) and outages in production systems, and thus, our proof reveals such catastrophes are potentially lurking behind every workload change. We then design FDR, the first cloned concurrency protocol to guarantee both monotonic prefix consistency and bounded replication lag. Further, we provide an implementation of FDR that is backward-compatible with existing production databases, making it possible to thwart these potential failures immediately. We demonstrate formally and experimentally FDR provides bounded replication lag under a variety of workloads. Reading List: Hong et al., KuaFu: Closing the parallelism gap in database replication, 2013. Wang et al., Query fresh: log shipping on steroids, 2017. Tu et al., Speedy transactions in multicore in-memory databases, 2013. Zheng et al., Fast Databases with Fast Durability and Recovery Through Multicore Parallelism, 2014. Corbett et al., Spanner: Google's globally distributed database, 2013. Thomson et al., Fast Distributed Transactions and Strongly Consistent Replication for OLTP Database Systems, 2014. Van Renesse and Schneider, Chain Replication for Supporting High Throughput and Availability, 2004. Terrace and Freedman, Object Storage on CRAQ: High-Throughput Chain Replication for Read-Mostly Workloads, 2009. Lamport, The part-time parliament. 1998. Papadimitriou, Serializability of Concurrent Database Updates, 1979. Herlihy and Wing, Linearizability: A correctness condition for concurrent objects, 1990. Textbooks: Tannenbaum and van Steen, Distributed Systems: Principles and Paradigms, 2017.

1 0

Hei Law will present his General Exam, "CornerNet-Lite: Efficient Keypoint Based Object Detection" on Monday, January 20, 2020 at 3:30pm in CS 401
by Nicki Mahler 13 Jan '20

13 Jan '20

Hei Law will present his General Exam, "CornerNet-Lite: Efficient Keypoint Based Object Detection" on Monday, January 20, 2020 at 3:30pm in CS 401. The members of his committee are as follows: Jia Deng (adviser), Adam Finkelstein, and Olga Russakovsky. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. Abstract: We propose CornerNet, a new approach to object detection where we detect an object bounding box as a pair of keypoints, the top-left corner and the bottom-right corner, using a single convolution neural network. By detecting objects as paired keypoints, we eliminate the need for designing a set of anchor boxes commonly used in prior single-stage detectors. In addition to our novel formulation, we introduce corner pooling, a new type of pooling layer that helps the network better localize corners. Experiments show that CornerNet achieves a 42.2% AP on COCO. However, this accuracy comes at high processing cost. We also tackle the problem of efficient keypoint-based object detection and introduce CornerNet-Lite. CornerNet-Lite is a combination of two efficient variants of CornerNet: CornerNet-Saccade, which uses an attention mechanism to eliminate the need for exhaustively processing all pixels of the image, and CornerNet-Squeeze, which introduces a new compact backbone architecture. Together these two variants address the two critical use cases in efficient object detection: improving efficiency without sacrificing accuracy, and improving accuracy at real-time efficiency. CornerNet-Saccade is suitable for offline processing, improving the efficiency of CornerNet by 6.0x and the AP by 1.0% on COCO. CornerNet-Squeeze is suitable for real-time detection, improving both the efficiency and accuracy of the popular real-time detector YOLOv3 (34.4% AP at 34ms for CornerNet-Squeeze compared to 33.0% AP at 39ms for YOLOv3 on COCO). Together these contributions for the first time reveal the potential of keypoint-based detection to be useful for applications requiring processing efficiency Reading List: 1. Szeliski, R. (2010). Computer vision: algorithms and applications. Springer Science & Business Media. 2. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 580-587). 3. Girshick, R. (2015). Fast r-cnn. In Proceedings of the IEEE international conference on computer vision (pp. 1440-1448). 4. Ren, S., He, K., Girshick, R., & Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. In Advances in neural information processing systems (pp. 91-99). 5. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 779-788). 6. Redmon, J., & Farhadi, A. (2017). YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 7263-7271). 7. Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016, October). Ssd: Single shot multibox detector. In European conference on computer vision (pp. 21-37). Springer, Cham. 8. Lin, T. Y., Goyal, P., Girshick, R., He, K., & Dollár, P. (2017). Focal loss for dense object detection. In Proceedings of the IEEE international conference on computer vision (pp. 2980-2988). 9. Tychsen-Smith, L., & Petersson, L. (2017). Denet: Scalable real-time object detection with directed sparse sampling. In Proceedings of the IEEE International Conference on Computer Vision (pp. 428-436). 10. Newell, A., Yang, K., & Deng, J. (2016, October). Stacked hourglass networks for human pose estimation. In European conference on computer vision (pp. 483-499). Springer, Cham. 11. Newell, A., Huang, Z., & Deng, J. (2017). Associative embedding: End-to-end learning for joint detection and grouping. In Advances in Neural Information Processing Systems (pp. 2277-2287).

1 0

Kaiyu Yang will present his General Exam on Monday, January 20, 2020 at 1:30pm in CS 402.
by Nicki Mahler 13 Jan '20

13 Jan '20

Kaiyu Yang will present his General Exam on Monday, January 20, 2020 at 1:30pm in CS 402. The members of his committee are as follows: Jia Deng (adviser), Szymon Rusinkiewicz, and Olga Russakovsky Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. Title: SpatialSense: An Adversarially Crowdsourced Benchmark for Spatial Relation Recognition Abstract: Understanding the spatial relations between objects in images is a surprisingly challenging task. A chair may be "behind" a person even if it appears to the left of the person in the image (depending on which way the person is facing). Two students that appear close to each other in the image may not in fact be "next to" each other if there is a third student between them. We introduce SpatialSense, a dataset specializing in spatial relation recognition which captures a broad spectrum of such challenges, allowing for proper benchmarking of computer vision techniques. SpatialSense is constructed through adversarial crowdsourcing, in which human annotators are tasked with finding spatial relations that are difficult to predict using simple cues such as 2D spatial configuration or language priors. Adversarial crowdsourcing significantly reduces dataset bias and samples more interesting relations in the long tail compared to existing datasets. On SpatialSense, state-of-the-art recognition models perform comparably to simple baselines, suggesting that they rely on straightforward cues instead of fully reasoning about this complex task. The SpatialSense benchmark provides a path forward to advancing the spatial reasoning capabilities of computer vision systems. Textbook: [1] Szeliski, Richard. Computer vision: algorithms and applications . Springer Science & Business Media, 2010. Papers: [2] Krishna, Ranjay, et al. "Visual genome: Connecting language and vision using crowdsourced dense image annotations." International Journal of Computer Vision 123.1 (2017): 32-73. [3] Kuznetsova, Alina, et al. "The open images dataset v4: Unified image classification, object detection, and visual relationship detection at scale." arXiv preprint arXiv:1811.00982 (2018). [4] Lu, Cewu, et al. "Visual relationship detection with language priors." European Conference on Computer Vision . Springer, Cham, 2016. [4] Torralba, Antonio, and Alexei A. Efros. "Unbiased look at dataset bias." CVPR . Vol. 1. No. 2. 2011. [5] Sadeghi, Mohammad Amin, and Ali Farhadi. "Recognition using visual phrases." CVPR 2011 . IEEE, 2011. [6] Dai, Bo, Yuqi Zhang, and Dahua Lin. "Detecting visual relationships with deep relational networks." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2017. [7] Xu, Danfei, et al. "Scene graph generation by iterative message passing." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2017. [8] Peyre, Julia, et al. "Weakly-supervised learning of visual relations." Proceedings of the IEEE International Conference on Computer Vision . 2017. [9] Goyal, Yash, et al. "Making the V in VQA matter: Elevating the role of image understanding in Visual Question Answering." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2017. [10] Zhang, Peng, et al. "Yin and yang: Balancing and answering binary visual questions." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition . 2016. [11] Attenberg, Josh M., Pagagiotis G. Ipeirotis, and Foster Provost. "Beat the machine: Challenging workers to find the unknown unknowns." Workshops at the Twenty-Fifth AAAI Conference on Artificial Intelligence . 2011.

1 0

Teague Tomesh will present his General Exam, "Minimizing State Preparations in Variational Quantum Eigensolver by Partitioning into Commuting Families" on Friday, January 17, 2020 at 1:30pm in CS 402.
by Nicki Mahler 10 Jan '20

10 Jan '20

Teague Tomesh will present his General Exam, "Minimizing State Preparations in Variational Quantum Eigensolver by Partitioning into Commuting Families" on Friday, January 17, 2020 at 1:30pm in CS 402. The members of his committee are as follows: Margaret Martonosi (adviser), Steve Lyon (EE), and Fred Chong (University of Chicago - Computer Science). Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. Variational quantum eigensolver (VQE) is a promising algorithm suitable for near-term quantum computers. VQE aims to approximate solutions to exponentially-sized optimization problems by executing a polynomial number of quantum subproblems. However, the number of subproblems scales as N^4 for typical problems of interest — a daunting growth rate that poses a serious limitation for emerging applications such as quantum computational chemistry. We mitigate this issue by exploiting the simultaneous measurability of subproblems corresponding to commuting terms. Our technique transpiles VQE instances into a format optimized for simultaneous measurement, yielding a linear-factor asymptotic improvement that translates to 8-30x lower cost for near term benchmarks. Our work also encompasses a synthesis tool for compiling simultaneous measurement circuits with minimal overhead. We demonstrate experimental validation of our techniques by estimating the ground state energy of deuteron with an IBM quantum computer. We also investigate the underlying statistics of simultaneous measurement and devise an adaptive strategy for mitigating harmful covariance terms. Textbook: Michael A Nielsen and Isaac L Chuang. Quantum computation and quantum information (10th anniv. version), 2010. Papers: 1. Richard Feynman. Simulating physics with computers. International Journal of Theoretical Physics, Vol 21, Now. 6/7, 1982 2. DiVincenzo, David P. "The physical implementation of quantum computation." Fortschritte der Physik: Progress of Physics/ 48, no. 9‐11 (2000): 771-783. 3. Peruzzo, Alberto, Jarrod McClean, Peter Shadbolt, Man-Hong Yung, Xiao-Qi Zhou, Peter J. Love, Alán Aspuru-Guzik, and Jeremy L. O’brien. "A variational eigenvalue solver on a photonic quantum processor." Nature communications 5 (2014): 4213. 4. Prakash Murali, Norbert Matthias Linke, Margaret Martonosi, Ali Javadi Abhari, Nhung Hong Nguyen, and Cinthia Huerta Alderete. 2019. Full-stack, real-system quantum computer studies: architectural comparisons and design insights. In Proceedings of the 46th International Symposium on Computer Architecture (ISCA '19). ACM, New York, NY, USA, 527-540. DOI: https://doi.org/10.1145/3307650.3322273 5. Preskill, John. "Quantum Computing in the NISQ era and beyond." Quantum 2 (2018): 79. 6. Tranter, Andrew, Peter J. Love, Florian Mintert, and Peter V. Coveney. "A Comparison of the Bravyi–Kitaev and Jordan–Wigner Transformations for the Quantum Simulation of Quantum Chemistry." Journal of chemical theory and computation 14, no. 11 (2018): 5617-5630. 7. X. Fu, M. A. Rol, C. C. Bultink, J. van Someren, N. Khammassi, I. Ashraf, R. F. L. Vermeulen, J. C. de Sterke, W. J. Vlothuizen, R. N. Schouten, C. G. Almudever, L. DiCarlo, and K. Bertels. 2017. An experimental microarchitecture for a superconducting quantum processor. In Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO-50 '17). ACM, New York, NY, USA, 813-825. DOI: https://doi.org/10.1145/3123939.3123952 8. Ravi Boppana and Magnús M Halldórsson. Approximating maximum independent sets by excluding subgraphs. BIT Numerical Mathematics, 32(2):180–196, 1992. 9. Jarrod R McClean,Jonathan Romero, Ryan Babbush, and Alán Aspuru-Guzik. The theory of variational hybrid quantum-classical algorithms. New Journal of Physics, 18(2):023023, 2016.

1 0

Alejandro Newell will present his General Exam "Beyond Objects: Image Understanding as Pixels to Graphs" on Friday, January 17, 2020 at 12pm in CS 401
by Nicki Mahler 10 Jan '20

10 Jan '20

Alejandro Newell will present his General Exam "Beyond Objects: Image Understanding as Pixels to Graphs" on Friday, January 17, 2020 at 12pm in CS 401. The members of his committee are as follows: Jia Deng (adviser), Olga Russakovsky, and Szymon Rusinkiewicz. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. Abstract: Tremendous progress has been made teaching computer vision systems to recognize objects in images. Each year, these systems can more reliably classify objects and better pinpoint their location in a scene. But a collection of objects is not enough. For full scene understanding, we must understand the connections and relationships between objects. Graphs are an effective way of representing these connections, but are difficult to express given standard approaches for training deep convolutional networks. In this presentation, I will discuss how to supervise a network to predict graphs. I will go over the details of our approach including its application to relationship detection and advantages over existing methods. Reading List: Szeliski, Richard. Computer vision: algorithms and applications. Springer Science & Business Media, 2010. Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012. Toshev, Alexander, and Christian Szegedy. "Deeppose: Human pose estimation via deep neural networks." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014. Tompson, Jonathan J., et al. "Joint training of a convolutional network and a graphical model for human pose estimation." Advances in neural information processing systems. 2014. Johnson, Justin, et al. "Image retrieval using scene graphs." Proceedings of the IEEE conference on computer vision and pattern recognition. 2015. He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016. Cao, Zhe, et al. "Realtime multi-person 2d pose estimation using part affinity fields." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. He, Kaiming, et al. "Mask r-cnn." Proceedings of the IEEE international conference on computer vision. 2017. Krishna, Ranjay, et al. "Visual genome: Connecting language and vision using crowdsourced dense image annotations." International Journal of Computer Vision 123.1 (2017): 32-73. Lu, Cewu, et al. "Visual relationship detection with language priors." European Conference on Computer Vision. Springer, Cham, 2016. Xu, Danfei, et al. "Scene graph generation by iterative message passing." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017. Oord, Aaron van den, Yazhe Li, and Oriol Vinyals. "Representation learning with contrastive predictive coding." arXiv preprint arXiv:1807.03748 (2018).

1 0

Ziyang Xu will present his General Exam "Revisiting Type-Awareness for Automatic Parallelization" on Friday, January 17, 2020 at 10:30am in CS 302
by Nicki Mahler 10 Jan '20

10 Jan '20

Ziyang Xu will present his General Exam "Revisiting Type-Awareness for Automatic Parallelization" on Friday, January 17, 2020 at 10:30am in CS 302. The members of his committee are as follows: David August (adviser), Amit Levy, and Zachary Kincaid. Everyone is invited to attend his talk, and those faculty wishing to remain for the oral exam following are welcome to do so. His abstract and reading list follow below. Abstract: Over the last decade, advances in memory analyses, speculative techniques, and parallelization paradigms have dramatically improved the power of automatic parallelization. To be applicable for general-purpose C and C++ codes, parallelizing compilers incorporating these advances work without making use of type information. This study explores the value of making RAPPORT, a state-of-the-art parallelization framework, aware of modern type features when parallelizing Rust programs. We extend RAPPORT with a Rust frontend that brings type information to the IR. New type-aware memory analysis (TAMA) modules bring this information into the RAPPORT's collaborative analysis framework (CAF), allowing these modules to use type information in collaborating with other memory analysis modules to maximize their effect. We measure the extent to which this framework can use Rust type information to uncover more or better automatic parallelization opportunities. Reading List: Books: [1]J. L. Hennessy and D. A. Patterson, Computer architecture: a quantitative approach. Elsevier, 2011. [2]A. W. Appel, Modern Compiler Implementation in ML. New York, NY, USA: Cambridge University Press, 2004. Papers: [1]B. K. Rosen, M. N. Wegman, and F. K. Zadeck, “Global value numbers and redundant computations,” in Proceedings of the 15th ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, 1988, pp. 12–27. [2]D. G. Clarke, J. M. Potter, and J. Noble, “Ownership Types for Flexible Alias Protection,” in Proceedings of the 13th ACM SIGPLAN Conference on Object-oriented Programming, Systems, Languages, and Applications, New York, NY, USA, 1998, pp. 48–64. [3]A. Diwan, K. S. McKinley, and J. E. B. Moss, “Type-based Alias Analysis,” in Proceedings of the ACM SIGPLAN 1998 Conference on Programming Language Design and Implementation, New York, NY, USA, 1998, pp. 106–117. [4]K. Crary, D. Walker, and G. Morrisett, “Typed memory management in a calculus of capabilities,” in Proceedings of the 26th ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages, POPL ’99, San Antonio, Texas, United States, 1999, pp. 262–275. [5]G. Ottoni, R. Rangan, A. Stoler, and D. I. August, “Automatic thread extraction with decoupled software pipelining,” in 38th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO’05), 2005, pp. 12 pp. – 118. [6]M. J. Bridges, N. Vachharajani, Y. Zhang, T. Jablin, and D. I. August, “Revisiting the Sequential Programming Model for Multi-Core,” in Proceedings of the 40th Annual IEEE/ACM International Symposium on Microarchitecture, pp. 69-84. IEEE Computer Society, 2007. [7]S. Campanoni, T. Jones, G. Holloway, V. J. Reddi, G.-Y. Wei, and D. Brooks, “HELIX: automatic parallelization of irregular programs for chip multiprocessing,” in Proceedings of the Tenth International Symposium on Code Generation and Optimization - CGO ’12, San Jose, California, 2012, p. 84. [8]N. P. Johnson, H. Kim, P. Prabhu, A. Zaks, and D. I. August, “Speculative Separation for Privatization and Reductions,” in Proceedings of the 33rd ACM SIGPLAN Conference on Programming Language Design and Implementation, New York, NY, USA, 2012, pp. 359–370. [9]N. P. Johnson, J. Fix, S. R. Beard, T. Oh, T. B. Jablin, and D. I. August, “A collaborative dependence analysis framework,” in 2017 IEEE/ACM International Symposium on Code Generation and Optimization (CGO), Austin, TX, USA, 2017, pp. 148–159. [10]V. Astrauskas, P. Müller, F. Poli, and A. J. Summers, “Leveraging Rust Types for Modular Specification and Verification,” Proc. ACM Program. Lang., vol. 3, no. OOPSLA, pp. 147:1–147:30, Oct. 2019. [11]S. Apostolakis, Z. Xu, G. Chan, S. Campanoni, and D. I. August, “Perspective: A Sensible Approach to Speculative Automatic Parallelization,” in Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems, 2020.

1 0