35 citations · 44 across the 6 of their papers we have counts for
6 papers
Maximizing Information in Domain-Invariant Representation Improves Transfer Learning
Adrian Shuai Li, Elisa Bertino, Xuan-Hong Dang +3
We propose MaxDIRep, a domain adaptation method that improves the decomposition of data representations into domain-independent and domain-dependent components. Existing methods, s…
Effective Dynamics of Generative Adversarial Networks
Steven Durr, Youssef Mroueh, Yuhai Tu +1
Generative adversarial networks (GANs) are a class of machine-learning models that use adversarial training to generate new samples with the same (potentially very complex) statist…
Stochastic gradient descent introduces an effective landscape-dependent regularization favoring flat solutions
Ning Yang, Chao Tang, Yuhai Tu
Generalization is one of the most important problems in deep learning (DL). In the overparameterized regime in neural networks, there exist many low-loss solutions that fit the tra…
The activity-weight duality in feed forward neural networks: The geometric determinants of generalization
Yu Feng, Yuhai Tu
One of the fundamental problems in machine learning is generalization. In neural network models with a large number of weights (parameters), many solutions can be found to fit the…
Loss Landscape Dependent Self-Adjusting Learning Rates in Decentralized Stochastic Gradient Descent
Wei Zhang, Mingrui Liu, Yu Feng +3
Distributed Deep Learning (DDL) is essential for large-scale Deep Learning (DL) training. Synchronous Stochastic Gradient Descent (SSGD) 1 is the de facto DDL optimization method.…
Search for WZ+ZZ production with MET + jets with b enhancement at sqrt(s) = 1.96 TeV
CDF Collaboration, T. Aaltonen, B. Álvarez Gonzálezv +513
Diboson production () has been observed at the Tevatron in hadronic decay modes dominated by the process. This paper describes the measurement of the cross section o…