Author of the publication

Train Feedfoward Neural Network with Layer-wise Adaptive Rate via Approximating Back-matching Propagation.

, , and . CoRR, (2018)

Please choose a person to relate this publication to

To differ between persons with the same name, the academic degree and the title of an important publication will be displayed. You can also use the button next to the name to display some publications already assigned to the person.

 

Other publications of authors with the same name

G-SGD: Optimizing ReLU Neural Networks in its Positively Scale-Invariant Space., , , , , , , and . ICLR (Poster), OpenReview.net, (2019)When and Why Momentum Accelerates SGD: An Empirical Study., , , , , and . CoRR, (2023)Indiscriminate Poisoning Attacks Are Shortcuts., , , , and . CoRR, (2021)Capacity Control of ReLU Neural Networks by Basis-Path Norm., , , , , and . AAAI, page 5925-5932. AAAI Press, (2019)Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart., , , , , , , and . CVPR, page 15202-15212. IEEE, (2022)Convergence of AdaGrad for Non-convex Objectives: Simple Proofs and Relaxed Assumptions., , , and . COLT, volume 195 of Proceedings of Machine Learning Research, page 161-190. PMLR, (2023)Does Momentum Change the Implicit Regularization on Separable Data?, , , , , , and . NeurIPS, (2022)Availability Attacks Create Shortcuts., , , , and . KDD, page 2367-2376. ACM, (2022)Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping., , , , , , , , and . ICLR, OpenReview.net, (2023)Membership Inference with Privately Augmented Data Endorses the Benign while Suppresses the Adversary., , , , and . CoRR, (2020)