Alessandro Epasto's Profile Picture

Alessandro Epasto

I am a senior staff research scientist at Google, New York working as Tech Lead of a privacy team in the Google Research Algorithms and Optimization group led by Vahab Mirrokni.

I received a Ph.D in computer science from Sapienza University of Rome, where I was advised by Professor Alessandro Panconesi and supported by the Google Europe Ph.D. Fellowship in Algorithms, 2011.

I was also a post-doc at the department of computer science of Brown University in Providence (RI), USA where I was advised by Professor Eli Upfal.

During my Ph.D. studies I was twice an intern at Google Mountain View (2012, 2014) and once at Google NYC (2013). 

My research interests include algorithmic problems in machine learning and data mining, in particular in the areas of privacy, clustering, and large scale graphs analysis.

CV

Publications

  • A. Epasto, H. Esfandiari, A.M. Medina, V. Mirrokni, "Smooth Anonymity for Sparse Graphs". In Companion Proceedings of the ACM on Web Conference 2024 WWW, [PDF], Best paper award at the 2nd Workshop on Trustworthy Learning on Graphs (TrustLOG), 2024

  • M.H. Bateni, V. Cohen-Addad, A. Epasto, S. Lattanzi, "A Scalable Algorithm for Individually Fair K-means Clustering". In Proceedings of 27th International Conference on Artificial Intelligence and Statistics AISTATS, [PDF], 2024

  • A. Epasto, V. Mirrokni, S. Narayanan, P. Zhong, "k-Means Clustering with Distance-Based Privacy". In Proceedings of the 36th Advances in Neural Information Processing Systems Neurips, [PDF], 2023

  • H. Chen, V. Cohen-Addad, T. d'Orsi, A. Epasto, J. Imola, D. Steurer, S. Tiegel, "Private estimation algorithms for stochastic block models and mixture models". In Proceedings of the 36th Advances in Neural Information Processing Systems Neurips, [PDF], 2023

  • C.J. Carey et al., "Measuring Re-identification Risk". In of Proceedings of the ACM on Management of Data Volume 1 Issue 2, SIGMOD 2023, [PDF], [code], 2023

  • J. Imola, A. Epasto, M. Mahdian, V. Cohen-Addad, V. Mirrokni "Differentially-Private Hierarchical Clustering with Provable Approximation Guarantees". In Proceedings of the Proceedings of the 40th International Conference on Machine Learning, ICML, Honolulu Hawaii[PDF],[code], 2023

  • A. Epasto, J. Mao, A. M. Medina, V. Mirrokni, S. Vassilvitskii, P. Zhong "Differentially Private Continual Releases of Streaming Frequency Moment Estimations". In Proceedings of the 14th Innovations in Theoretical Computer Science Conference, ITCS, Cambridge Massachusetts[PDF], 2023

  • V. Cohen-Addad, A. Epasto, V. Mirrokni, S. Narayanan, P. Zhong "Near-Optimal Private and Scalable k-Clustering". In Proceedings of the 35th Advances in Neural Information Processing Systems, NeurIPS, New Orleans [PDF], 2022

  • A. Epasto, V. Mirrokni, B. Perozzi, A. Tsitsulin, P. Zhong"Differentially private graph learning via sensitivity-bounded Personalized PageRank". In Proceedings of the 35th Advances in Neural Information Processing Systems, NeurIPS, New Orleans [PDF], [code], 2022

  • V. Cohen-Addad, A. Epasto, S. Lattanzi, V. Mirrokni, A. Munoz Medina, D. Saulpic, C. Schwiegelshohn, S. Vassilvitskii "Scalable differentially private clustering via hierarchically separated trees"". In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD, Washington, DC, [PDF], [code], 2022

  • M. Almanza, A. Epasto, A. Panconesi, G. Re. "k-Clustering with Fair Outliers". In Proceedings of the Fifteenth International Conference on Web Search and Data Mining, WSDM, Phoenix, Arizona, [PDF], [code], 2022

  • A. Epasto, M. Mahdian, V. Mirrokni, P. Zhong "Massively Parallel and Dynamic Algorithms for Minimum Size Clustering". In Proceedings of the ACM-SIAM Symposium on Discrete Algorithms, SODA, Alexandria, Virginia, [PDF], 2022

  • A. Epasto, M. Mahdian, V. Mirrokni, P. Zhong "Improved Sliding Window Algorithms for Clustering and Coverage via Bucketing-Based Sketches". In Proceedings of the ACM-SIAM Symposium on Discrete Algorithms, SODA, Alexandria, Virginia [PDF],  2022

  • A. Epasto, A. Muñoz Medina, et al. "Clustering for Private Interest-based Advertising". In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD Ads Track, Virtual [PDF], 2021

  • M. Borassi, A. Epasto, S. Lattanzi, S. Vassilvitskii, M. Zadimoghaddam, "Sliding Window Algorithms for k-Clustering Problems". In Proceedings of the 34th Conference on Neural Information Processing Systems, NeurIPS, Vancouver, Canada, [pre-print], [code],  2020

  • S. Ahmadian, A. Epasto, M. Knittel, R. Kumar, M. Mahdian, B. Moseley, P. P., S. Vassilvitskii, Y. Wang, "Fair Hierarchical Clustering". In Proceedings of the 34th Conference on Neural Information Processing Systems, NeurIPS, Vancouver, Canada, [pre-print], [code],  2020

  • A. Epasto, M. Mahdian, V. Mirrokni, E. Zampetakis "Optimal Approximation - Smoothness Tradeoffs for Soft-Max Functions". In Proceedings of the 34th Conference on Neural Information Processing Systems, NeurIPS, Vancouver, Canada, [pre-print], ,  2020

  • A. Epasto, M. Mahdian, J. Mao, V. Mirrokni, L. Ren"Smoothly Bounding User Contributions in Differential Privacy". In Proceedings of the 34th Conference on Neural Information Processing Systems, NeurIPS, Vancouver, Canada, ,  2020

  • S. Ahmadian, A. Epasto, M. Mahdian, R. Kumar, "Fair Correlation Clustering". In Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, AISTATS, Palermo, Italy [pre-print], [code], [talk]  2020

  • S. Ahmadian, V. Chatziafratis, A. Epasto, E. Lee, M. Mahdian, K. Makarychev, G. Yaroslavtsev, "Bisect and Conquer: Hierarchical Clustering via Max-Uncut Bisection". In Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, AISTATS, Palermo, Italy [pre-print], 2020

  • S. Ahmadian, A. Epasto, M. Mahdian, R. Kumar, "Clustering without Over-Representation". In Proceedings of the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD, Anchorage, AK [PDF], 2019

  • M. Borassi, A. Epasto, S. Lattanzi, S. Vassilvitskii, M. Zadimoghaddam "Better Sliding Window Algorithms to Maximize Subadditive and Diversity Objectives". In Proceedings of the 38th Symposium on Principles of Database Systems, PODS, Amsterdam, The Netherlands [PDF], 2019

  • A. Epasto, V. Mirrokni, M. Zadimoghaddam "Scalable diversity maximization via small-size composable core-sets". In Proceedings of the 31st ACM Symposium on Parallelism in Algorithms and Architectures, brief announcement, SPAA, Phoenix, AZ [PDF], 2019

  • A. Epasto, H. Esfandiari, V. Mirrokni , "On-Device Algorithms for Public-Private Data with Absolute Privacy". In Proceedings of The Web Conference 2019, WWW, San Francisco, CA, [PDF], 2019 (Also, best poster award honorable mention at New York Academy of Sciences, Machine Learning Symposium)

  • A. Epasto, B. Perozzi, "Is a Single Embedding Enough? Learning Node Representations that Capture Multiple Social Contexts". In Proceedings of The Web Conference 2019, WWW, San Francisco, CA, [PDF], [Code] 2019

  • A. Epasto, E. Upfal, "Efficient Approximation for Restricted Biclique Cover Problems". Algorithms 11(6), 84, [PDF], 2018

  • A. Epasto, M. Mahdian, V. Mirrokni, S. Zuo, "Incentive-aware learning for large markets". In Proceedings of the 27th International Conference on World Wide Web, WWW, Lyon, France, [Conference Version], 2018

  • A. Epasto, S. Lattanzi, and R. P. Leme "Ego-splitting Framework: from Non-Overlapping to Overlapping Clusters". In Proceedings of the 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD, Halifax, Canada, [Conference version], [Slides] [Code] 2017

  • A. Epasto, A. Mahmoody and E. Upfal "Real-Time Targeted-Influence Queries over Large Graphs". In Proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM, Sydney, Australia, [Conference Version], 2017

  • A. Epasto, V. Mirrokni and M. Zadimoghaddam "Bicriteria Distributed Submodular Maximization in a Few Rounds". In Proceedings of 29th ACM Symposium on Parallelism in Algorithms and Architectures, SPAA, Washington DC, USA, [Conference Version], 2017

  • L. De Stefani, A. Epasto, M. Riondato, E. Upfal "TRIÈST: Counting Local and Global Triangles in Fully-dynamic Streams with Fixed Memory Size". In ACM Transactions on Knowledge Discovery from Data, TKDD, [Pre-Print], [Code], In press 2017

  • A. Epasto, S. Lattanzi, S. Vassilvitskii, M. Zadimoghaddam "Submodular Optimization over Sliding Windows". In Proceedings of the 26th International World Wide Web Conference WWW, Perth, Australia, [Conference Version], [Full Version], 2017

  • D. Stück, H. T. Hallgrímsson, G. V. Steeg, A. Epasto, L. Foschini, "The Spread of Physical Activity in Social Networks". In Proceedings of the 26th International World Wide Web Conference WWW, Perth, Australia, [Conference Version], 2017

  • L. De Stefani, A. Epasto, M. Riondato, E. Upfal "TRIÈST: Counting Local and Global Triangles in Fully-dynamic Streams with Fixed Memory Size". In Proceedings of the 22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD, San Francisco, CA, [Conference Version], [Full Version], [Poster], [Code], 2016 Best student paper award

  • L. De Stefani, A. Epasto, E. Upfal, F. Vandin , "Reconstructing Hidden Permutations Using the Average-Precision (AP) Correlation Statistic". In Proceedings of the 30th AAAI Conference on Artificial Intelligence, AAAI, Phoenix, Arizona, USA, [PDF], [Full Version], [Poster], [Code], 2016

  • A. Epasto, S. Lattanzi, V. Mirrokni, I. Sebe, A. Taei and S. Verma , "Ego-net Community Mining Applied to Friend Suggestion". In Proceedings of the 42nd International Conference on Very Large Data Bases, VLDB, New Delhi, India, [PDF], 2016

  • F. Chierichetti, A. Epasto, R. Kumar, S. Lattanzi and V. Mirrokni, "Efficient Algorithms for Private-Public Graphs". In Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD, Sydney, Australia, [PDF], [Slides], [Poster], [Code], 2015, Best paper award

  • A. Epasto, S. Lattanzi and M. Sozio , "Efficient Densest Subgraph Computation in Evolving Graphs". In Proceedings of the 24th International World Wide Web Conference, WWW, Florence, Italy, [PDF], [Slides], [Code], 2015

  • P. Brach, A. Epasto, A. Panconesi and P. Sankovski , "Spreading Rumours without the Network". In Proceedings of the 2nd ACM Conference on Social Networks, COSN, Dublin, Ireland, [PDF], [Slides], 2014

  • A. Epasto, J. Feldman, S. Lattanzi, S. Leonardi and V. Mirrokni , "Reduce and Aggregate: Similarity Rankings in Multi-Categorical Bipartite Graphs". In Proceedings of the 23rd International World Wide Web Conference, WWW, Seoul, Korea, [PDF], [Slides], 2014

  • L. Alvisi, A. Clement, A. Epasto, S. Lattanzi and A. Panconesi , "Communities, Random Walks and Sybil Defense". In Internet Mathematics, [PDF], [Pre-Print], Vol. 10, Issue 3-4, 2014

  • M.V. Barbera, A. Epasto, A. Mei, C. Perta and J. Stefa, "Signals from the Crowd: Uncovering Social Relationships through Smartphone Probes", In Proceedings of 13th ACM/SIGCOMM Conference on Internet Measurement, IMC, Barcelona, Spain, [PDF], [Data], 2013

  • L. Alvisi, A. Clement, A. Epasto, S. Lattanzi and A. Panconesi, "SoK: The Evolution of Sybil Defense via Social Networks", In Proceedings of the 34th IEEE Symposium on Security and Privacy, S&P, San Francisco, USA, [PDF], [Slides], 2013

Patents

  • A. Epasto, H. Esfandiari, V.S. Mirrokni, A.M. Medina, U. Syed, S. Vassilvitskii, "Systems and methods for anonymizing large scale datasets" United States Patent 11,727,147, [PDF], 2023

  • A. Epasto, H. Esfandiari, V. Mirrokni, "Efficient On-Device Public-Private Computation" United States Patent 11,574,067, [PDF], 2023

  • A. Epasto, R.P.P. Leme, S Lattanzi. "Systems and Methods to Detect Clusters in Graphs" . United States Patent 11,829,416, [PDF], 2023

  • A. Epasto and B. Perozzi. "Methods and Systems for Encoding Graphs" . United States Patent 11,100,688, [PDF] 2021

  • V. Mirrokni, S. Lattanzi, J. Feldman, A. Epasto, S. Leonardi, "Efficient Similarity Ranking for Bipartite Graphs" . United States Patent 10,152,557, [PDF], 2018

  • A. Epasto and A. Altman, "Systems and Methods for Detecting Online Attacks" . United States Patent 9,183,387 [PDF], 2015

Service as Reviewer and Program Committee (Selected Conferences):

  • NeurIPS: Reviewer 2020-2023.

  • KDD: PC 2016-2023.

  • ICML: Reviewer 2020-2023.

  • WSDM: PC 2016-2023. Senior PC 2024

  • WWW (The Web Conference): PC 2017-2024. Senior PC 2022, 2023


    •  

Contact

Google New York 76 Ninth Avenue New York, NY, 10011
(212) 565-0000
mail: aepasto at google.com

Links

Google Scholar DBLP LinkedIn Google AI Orcid.org ResearcherID.com Research Gate Microsoft Academic Semantic Scholar