Neural Information Processing Systems http://nips.cc/

We revisit data selection in a modern context of finetuning from a fundamental perspective.

Though promising results have been reported on some RL application domains, policies learned with such representations usually fail to generalize well in a complex environment because minimizing a reconstruction loss may potentially introduce local (visual) features with task-irrelevant information.

Though promising results have been reported on some RL application domains, policies learned with such representations usually fail to generalize well in a complex environment because minimizing a reconstruction loss may potentially introduce local (visual) features with task-irrelevant information.

We study gradient-based optimization methods obtained by directly discretizing a second-order ordinary differential equation (ODE) related to the continuous limit of Nesterov's accelerated gradient method.

Neural Information Processing Systems http://nips.cc/

We also calculate the optimal solution to verify the approximation ratio. See Table 1 in our submission for definitions. It is indeed an interesting problem to generalize our techniques to other problems, e.g., classification problems and40 non-linearregressionproblems.