Showing 1–20 of 29 results
/ Date/ Name
Jul 3, 2022Tricking the Hashing Trick: A Tight Lower Bound on the Robustness of CountSketch to Adaptive InputsDec 4, 2023SARA-RT: Scaling up Robotics Transformers with Self-Adaptive Robust AttentionOct 25, 2020Differentially Private Weighted SamplingDec 4, 2023Hot PATE: Private Aggregation of Distributions for Diverse TaskNov 10, 2024One Attack to Rule Them All: Tight Quadratic Bounds for Adaptive Queries on Cardinality SketchesNov 3, 2023Hardness of Low Rank Approximation of Entrywise Transformed Matrix ProductsFeb 2, 2023Efficient Graph Field Integrators Meet Point CloudsFeb 3, 2023Learning a Fourier Transform for Linear Relative Positional Encodings in TransformersAug 13, 2014Fastfood: Approximate Kernel Expansions in Loglinear TimeSep 30, 2020Rethinking Attention with PerformersJul 16, 2021From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked TransformersOct 7, 2007Faster Least Squares ApproximationJun 22, 2024Fast Tree-Field Integrators: From Low Displacement Rank to Topological TransformersOct 19, 2016Structured adaptive and random spinners for fast machine learning computationsJun 5, 2020Masked Language Modeling for Proteins via Linearly Scalable Long-Context TransformersMar 9, 2019Orthogonal Estimation of Wasserstein DistancesFeb 28, 2024Lower Bounds for Differential Privacy Under Continual Observation and Online Threshold QueriesNov 11, 2022Õptimal Differentially Private Learning of Thresholds and Quasi-Concave OptimizationFeb 1, 2023FAVOR#: Sharp Attention Kernel Approximations via New Classes of Positive Random FeaturesMay 29, 2019Matrix-Free Preconditioning in Online Learning