output
20022026
most citedPublicly Available Clinical BERT Embeddings

732 citations

Showing 2022 · cs.LGShow all

6 papers · 2 filters

cs.LG2022★ 2 cited

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…

cs.LG2022★ 17 cited

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…

cs.LG2022★ 51 cited

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…

cs.LG2022★ 10 cited

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…

cs.LG2022★ 13 cited

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…

cs.LG2022★ 14 cited

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…