Optimization
Reward is Enough for Convex MDPs
Maximising a cumulative reward function that is Markov and stationary, i.e., defined over state-action pairs and independent of time, is sufficient to capture many
Universal Boosting Variational Inference
But theguarantees have strong conditions that donot often hold inpractice, resulting indegenerate component optimization problems; and weshowthat the ad-hoc regularization used to prevent degeneracyin practice can cause BVI to fail in unintuitiveways.
Meta-Learning with Implicit Gradients
Aravind Rajeswaran, Chelsea Finn, Sham M. Kakade, Sergey Levine
A core aspect of intelligence is the ability to quickly learn new tasks by drawing upon prior experience from related tasks. Recent work has studied how meta-learning algorithms [51, 55, 41] can acquire such a capability by learning to efficiently learn a range of tasks, thereby enabling learning of a new task with as little as a single example [50, 57, 15].
Meta-Surrogate Benchmarking for Hyperparameter Optimization
Aaron Klein, Zhenwen Dai, Frank Hutter, Neil Lawrence, Javier Gonzalez
The model combines aprobabilistic encoder withamulti-task model suchthatitcan generate inexpensive and realistic tasks of the class of problems of interest.
Efficient Algorithms for Smooth Minimax Optimization
Kiran K. Thekumparampil, Prateek Jain, Praneeth Netrapalli, Sewoong Oh
In terms of g(, y), we consider two settings - strongly convex and nonconvex - and improve upon the best known rates in both. For strongly-convex g(, y), y, we propose a new direct optimal algorithm combining Mirror-Prox and Nesterov's AGD, and show that it can find global optimum in Õ (1/k
