Search Results for author:
Found 5 papers, 1 papers with code
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
We exploit this novel setting to study the training and generalization properties of the GN optimizer.
Sample-efficient Bayesian Optimisation Using Known Invariances
We derive a bound on the maximum information gain of these invariant kernels, and provide novel upper and lower bounds on the number of observations required for invariance-aware BO algorithms to achieve $\epsilon$-optimality.
Flexible Multiple-Objective Reinforcement Learning for Chip Placement
Recently, successful applications of reinforcement learning to chip placement have emerged.
How to distribute data across tasks for meta-learning?
We show that: 1) If tasks are homogeneous, there is a uniform optimal allocation, whereby all tasks get the same amount of data; 2) At fixed budget, there is a trade-off between number of tasks and number of data points per task, with a unique solution for the optimum; 3) When trained separately, harder task should get more data, at the cost of a smaller number of tasks; 4) When training on a mixture of easy and hard tasks, more data should be allocated to easy tasks.
Optimal allocation of data across training tasks in meta-learning
They are tested on benchmarks with a fixed number of data-points for each training task, and this number is usually arbitrary, for example, 5 instances per class in few-shot classification.
