5 papers
Beyond Johnson-Lindenstrauss: Uniform Bounds for Sketched Bilinear Forms
Rohan Deb, Qiaobo Li, Mayank Shrivastava +1
Uniform bounds on sketched inner products of vectors or matrices underpin several important computational and statistical results in machine learning and randomized algorithms, inc…
Sketched Gaussian Mechanism for Private Federated Learning
Qiaobo Li, Zhijie Chen, Arindam Banerjee
Communication cost and privacy are two major considerations in federated learning (FL). For communication cost, gradient compression by sketching the clients' transmitted model upd…
Sketched Adaptive Federated Deep Learning: A Sharp Convergence Analysis
Zhijie Chen, Qiaobo Li, Arindam Banerjee
Combining gradient compression methods (e.g., CountSketch, quantization) and adaptive optimizers (e.g., Adam, AMSGrad) is a desirable goal in federated learning (FL), with potentia…
Loss Gradient Gaussian Width based Generalization and Optimization Guarantees
Arindam Banerjee, Qiaobo Li, Yingxue Zhou
Generalization and optimization guarantees on the population loss often rely on uniform convergence based analysis, typically based on the Rademacher complexity of the predictors.…
Differentially Private Post-Processing for Fair Regression
Ruicheng Xian, Qiaobo Li, Gautam Kamath +1
This paper describes a differentially private post-processing algorithm for learning fair regressors satisfying statistical parity, addressing privacy concerns of machine learning…