Optimization
Pareto Multi-Task Learning
Xi Lin, Hui-Ling Zhen, Zhenhua Li, Qing-Fu Zhang, Sam Kwong
Theproposed algorithm first formulates a multi-task learning problem as a multiobjective optimization problem, and then decomposes the multiobjective optimization problem into a set of constrained subproblems with different trade-off preferences.
Maximum Causal Tsallis Entropy Imitation Learning
Kyungjae Lee, Sungjoon Choi, Songhwai Oh
Neural Information Processing Systems http://nips.cc/
Riemannian stochastic optimization methods avoid strict saddle points Anonymous Author(s) Affiliation Address email
Riemannian setting is a highly challenging affair.
The Landscape of Non-convex Empirical Risk with Degenerate Population Risk
Shuang Li, Gongguo Tang, Michael B. Wakin
Neural Information Processing Systems http://nips.cc/
