Author of the publication

Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks.

, , 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

On the necessity of irrelevant variables., and . J. Mach. Learn. Res., (2012)Adaptive disk spin-down for mobile computers., , , and . Mob. Networks Appl., 5 (4): 285-297 (2000)Determining Possible Event Orders by Analyzing Sequential Traces., , and . IEEE Trans. Parallel Distributed Syst., 4 (7): 827-840 (1993)Improved Lower Bounds for Learning from Noisy Examples: An Information-Theoretic Approach., and . COLT, page 104-115. ACM, (1998)Combining Initial Segments of Lists., , and . ALT, volume 6925 of Lecture Notes in Computer Science, page 219-233. Springer, (2011)Gradient descent with identity initialization efficiently learns positive definite linear transformations., , and . ICML, volume 80 of Proceedings of Machine Learning Research, page 520-529. PMLR, (2018)Online Learning Using Only Peer Assessment., and . CoRR, (2019)Modeling Speedup greater than n., and . ICPP (3), page 219-225. Pennsylvania State University Press, (1989)0-271-00686-2.On-Line Portfolio Selection Using Multiplicative Updates., , , and . ICML, page 243-251. Morgan Kaufmann, (1996)Modeling, analyzing, and synthesizing expressive piano performance with graphical models., and . Mach. Learn., 65 (2-3): 361-387 (2006)