Optimization

Optimization or Architecture: How to Hack Kalman Filtering

Since the KF assumptions are often violated, noise estimation is not a proxy to MSE optimization. Instead, our method (OKF) optimizes the MSE directly. In particular, neural network models should be tested against OKF rather than the non-optimized KF – in contrast to the common practice in the literature.

GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning

Video Abstract Gaussian processes (GPs) are non-parametric, flexible, models that work well in many tasks. Combining GPs with deep learning methods via deep kernel learning is especially compelling due to the strong expressive power induced by the network.

Auxiliary Learning by Implicit Differentiation

Video Abstract Training with multiple auxiliary tasks is a common practice used in deep learning for improving the performance on the main task of interest. Two main challenges arise in this multi-task learning setting: (i) Designing useful auxiliary tasks; and (ii) Combining auxiliary tasks into a single coherent loss.

Learning the Pareto Front with Hypernetworks

Video Abstract Multi-objective optimization problems are prevalent in machine learning. These problems have a set of optimal solutions, called the Pareto front, where each point on the front represents a different trade-off between possibly conflicting objectives.