TR
Theodoros Rekatsinas
cs.LGcs.DBstat.MLcs.AIcs.CLcs.DCcs.CVcs.IRcs.DScs.NE
On Valency
published · living versionsW_u7fa5rax·v1 · currentpublished
MLSys: The New Frontier of Machine Learning Systems
with Alexander Ratner, Dan Alistarh, Gustavo Alonso, David G. Andersen +64
1 version
Preprints & journals
36 papers in the corpus · 2013–2025Quake: Adaptive Indexing for Vector Search2506.03437v2 · Jason Mohoney, Devesh Sarda, Mengze Tang et al.2025 · 0 citationsarXiv
MLKV: Efficiently Scaling up Large Embedding Model Training with Disk-based Key-Value Storage2504.01506v1 · Yongjun He, Roger Waleffe, Zhichao Han et al.2025 · 1 citationarXiv
Armada: Memory-Efficient Distributed Training of Large-Scale Graph Neural Networks2502.17846v1 · Roger Waleffe, Devesh Sarda, Jason Mohoney et al.2025 · 0 citationsarXiv
Fundamental Challenges in Evaluating Text2SQL Solutions and Detecting Their Limitations2501.18197v1 · Cedric Renggli, Ihab F. Ilyas, Theodoros Rekatsinas2025 · 2 citationsarXiv
TSDS: Data Selection for Task-Specific Model Finetuning2410.11303v3 · Zifan Liu, Amin Karbasi, Theodoros Rekatsinas2024 · 2 citationsarXiv
Incremental IVF Index Maintenance for Streaming Vector Search2411.00970v1 · Jason Mohoney, Anil Pacaci, Shihabur Rahman Chowdhury et al.2024 · 0 citationsarXiv
Open Domain Knowledge Extraction for Knowledge Graphs2312.09424v1 · Kun Qian, Anton Belyi, Fei Wu et al.2023 · 0 citationsarXiv
Construction of Paired Knowledge Graph-Text Datasets Informed by Cyclic Evaluation2309.11669v1 · Ali Mousavi, Xin Zhan, He Bai et al.2023 · 0 citationsarXiv
EnergAt: Fine-Grained Energy Attribution for Multi-Tenancy2307.05647v2 · Hongyu He, Michal Friedman, Theodoros Rekatsinas2023 · 8 citationsThe 2nd Workshop on Sustainable Computer Systems (HotCarbon '23), July 9, 2023, Boston, MA, USA. ACM, New York, NY, USA, 8 pages
Co-design Hardware and Algorithm for Vector Search2306.11182v3 · Wenqi Jiang, Shigang Li, Yu Zhu et al.2023 · 21 citationsarXiv
Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning2305.18424v1 · Patrik Okanovic, Roger Waleffe, Vasilis Mageirakos et al.2023 · 7 citationsarXiv
Growing and Serving Large Open-domain Knowledge Graphs2305.09464v1 · Ihab F. Ilyas, JP Lacerda, Yunyao Li et al.2023 · 3 citationsarXiv
High-Throughput Vector Similarity Search in Knowledge Graphs2304.01926v1 · Jason Mohoney, Anil Pacaci, Shihabur Rahman Chowdhury et al.2023 · 44 citationsarXiv
MariusGNN: Resource-Efficient Out-of-Core Training of Graph Neural Networks2202.02365v2 · Roger Waleffe, Jason Mohoney, Theodoros Rekatsinas et al.2022 · 42 citationsarXiv
Saga: A Platform for Continuous Construction and Serving of Knowledge At Scale2204.07309v1 · Ihab F. Ilyas, Theodoros Rekatsinas, Vishnu Konda et al.2022 · 21 citationsACM SIGMOD 2022
Picket: Guarding Against Corrupted Data in Tabular Data during Learning and Inference2006.04730v3 · Zifan Liu, Zhechun Zhou, Theodoros Rekatsinas2020 · 23 citationsarXiv
On Robust Mean Estimation under Coordinate-level Corruption2002.04137v5 · Zifan Liu, Jongho Park, Theodoros Rekatsinas et al.2020 · 3 citationsarXiv
Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins2106.01501v1 · Sahaana Suri, Ihab F. Ilyas, Christopher R'e et al.2021 · 1 citationarXiv
Marius: Learning Massive Graph Embeddings on a Single Machine2101.08358v2 · Jason Mohoney, Roger Waleffe, Yiheng Xu et al.2021 · 12 citationsarXiv
Unsupervised Relation Extraction from Language Models using Constrained Cloze Completion2010.06804v1 · Ankur Goswami, Akshata Bhat, Hadar Ohana et al.2020 · 11 citationsarXiv
Data-Dependent Differentially Private Parameter Learning for Directed Graphical Models1905.12813v3 · Amrita Roy Chowdhury, Theodoros Rekatsinas, Somesh Jha2019 · 9 citationsarXiv
Principal Component Networks: Parameter Reduction Early in Training2006.13347v1 · Roger Waleffe, Theodoros Rekatsinas2020 · 3 citationsarXiv
Record fusion: A learning approach2006.10208v1 · Alireza Heidari, George Michalopoulos, Shrinu Kushagra et al.2020 · 5 citationsarXiv
An Empirical Analysis of the Impact of Data Augmentation on Knowledge Distillation2006.03810v2 · Deepan Das, Haley Massa, Abhimanyu Kulkarni et al.2020 · 13 citationsarXiv
MLSys: The New Frontier of Machine Learning Systems1904.03257v3 · Alexander Ratner, Dan Alistarh, Gustavo Alonso et al.2019 · 20 citationsarXivon Valency
Fine-Grained Object Detection over Scientific Document Images with Region Embeddings1910.12462v2 · Ankur Goswami, Joshua McGrath, Shanan Peters et al.2019 · 3 citationsarXiv
Approximate Inference in Structured Instances with Noisy Categorical Observations1907.00141v2 · Alireza Heidari, Ihab F. Ilyas, Theodoros Rekatsinas2019 · 5 citationsarXiv
Learning Functional Dependencies with Sparse Regression1905.01425v1 · Zhihan Guo, Theodoros Rekatsinas2019 · 0 citationsarXiv
A Formal Framework For Probabilistic Unclean Databases1801.06750v3 · Christopher De Sa, Ihab F. Ilyas, Benny Kimelfeld et al.2018 · 32 citationsarXiv
Fonduer: Knowledge Base Construction from Richly Formatted Data1703.05028v2 · Sen Wu, Luke Hsiao, Xiao Cheng et al.2017 · 80 citationsSIGMOD 2018
HoloClean: Holistic Data Repairs with Probabilistic Inference1702.00820v1 · Theodoros Rekatsinas, Xu Chu, Ihab F. Ilyas et al.2017 · 54 citationsarXiv
SLiMFast: Guaranteed Results for Data Fusion and Source Reliability1512.06474v3 · Manas Joglekar, Theodoros Rekatsinas, Hector Garcia-Molina et al.2015 · 8 citationsarXiv
CrowdGather: Entity Extraction over Structured Domains1502.06823v1 · Theodoros Rekatsinas, Amol Deshpande, Aditya Parameswaran2015 · 3 citationsarXiv
Multi-relational Learning Using Weighted Tensor Decomposition with Modular Loss1303.1733v2 · Ben London, Theodoros Rekatsinas, Bert Huang et al.2013 · 15 citationsarXiv
On Sharing Private Data with Multiple Non-Colluding Adversaries1302.6556v3 · Theodoros Rekatsinas, Amol Deshpande, Ashwin Machanavajjhala2013 · 0 citationsarXiv
Career total: 85 works. 36 are in this corpus.Showing the 35 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.