Search for tag: "arc12 distinguished lecture"
Galyna Livshyts - A Tight Net with Respect to a Random Matrix Norm and Applications to Estimating Singular ValuesIn this talk we construct a net around the unit sphere with good properties. We show that with exponentially high probability, the value of |Ax| on the sphere can be approximated well using this net,…
From Katie Gentilello
68 plays
0
|
|
Tuo Zhao - Towards Understanding First Order Algorithms for Nonconvex Optimization in Machine LearningStochastic Gradient Descent-type (SGD) algorithms have been widely applied to many non-convex optimization problems in machine learning, e.g., training deep neural networks, variational Bayesian…
From Katie Gentilello
63 plays
0
|
|
Éva Tardos - Learning and Efficiency of Outcomes in GamesSelfish behavior can often lead to suboptimal outcome for all participants, a phenomenon illustrated by many classical examples in game theory. Over the last decade we have studied Nash equilibria…
From Katie Gentilello
144 plays
0
|