collaborators

5 papers

cs.LG2025

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…

cs.LG2025

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…

cs.LG2025

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.…

cs.LG2025

Optimization for Neural Operators can Benefit from Width

Pedro Cisneros-Velarde, Bhavesh Shrimali, Arindam Banerjee

Neural Operators that directly learn mappings between function spaces, such as Deep Operator Networks (DONs) and Fourier Neural Operators (FNOs), have received considerable attenti…

cs.LG2025

Optimization and Generalization Guarantees for Weight Normalization

Pedro Cisneros-Velarde, Zhijie Chen, Sanmi Koyejo +1

Weight normalization (WeightNorm) is widely used in practice for the training of deep neural networks and modern deep learning libraries have built-in implementations of it. In thi…