732 citations
- Microsoft (United States)US99 papers
- Carnegie Mellon UniversityUS41 papers
- Massachusetts Institute of TechnologyUS41 papers
- University of WashingtonUS39 papers
- Stanford UniversityUS32 papers
- University of CambridgeGB31 papers
- University of Science and Technology of ChinaCN31 papers
- Peking UniversityCN28 papers
- University of California, BerkeleyUS28 papers
- Tsinghua UniversityCN24 papers
- University College LondonGB24 papers
- Microsoft Research Asia (China)CN19 papers
6 papers · 2 filters
Methods for Recovering Conditional Independence Graphs: A Survey
Harsh Shrivastava, Urszula Chajewska
Conditional Independence (CI) graphs are a type of probabilistic graphical models that are primarily used to gain insights about feature relationships. Each edge represents the par…
Membership Inference Attacks and Generalization: A Causal Perspective
Teodora Baluta, Shiqi Shen, S. Hitarth +2
Membership inference (MI) attacks highlight a privacy weakness in present stochastic training methods for neural networks. It is not well understood, however, why they arise. Are t…
Adaptive Bias Correction for Improved Subseasonal Forecasting
Soukayna Mouatadid, Paulo Orenstein, Genevieve Flaspohler +4
Subseasonal forecasting -- predicting temperature and precipitation 2 to 6 weeks ahead -- is critical for effective water allocation, wildfire management, and drought and flood mit…
Bayesian Estimation of Differential Privacy
Santiago Zanella-Béguelin, Lukas Wutschitz, Shruti Tople +6
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, there is a discrepancy between the protection that su…
LordNet: An Efficient Neural Network for Learning to Solve Parametric Partial Differential Equations without Simulated Data
Xinquan Huang, Wenlei Shi, Xiaotian Gao +5
Neural operators, as a powerful approximation to the non-linear operators between infinite-dimensional function spaces, have proved to be promising in accelerating the solution of…
Results of the NeurIPS'21 Challenge on Billion-Scale Approximate Nearest Neighbor Search
Harsha Vardhan Simhadri, George Williams, Martin Aumüller +9
Despite the broad range of algorithms for Approximate Nearest Neighbor Search, most empirical evaluations of algorithms have focused on smaller datasets, typically of 1 million poi…