Statistical Learning
Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
Scaling hyperparameter optimisation to very large datasets remains an open problem in the Gaussian process community.
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
The resulting features are evaluated on k-nearest neighbor classification over 11 datasets from vision, 5 from natural language processing, and 2 from audio.
AT Proofs
We then follow the proof of Theorem 3 in Farnia and Tse [2016]. Our formulation differs from Nowak-Vila et al. [2020] in the fact that we allow probabilistic prediction to be ground truth. Proposition 4. Let G be a multi-graph. We follow the proof of Friesen [2019] for simple graphs. Proposition 5. Let G be a multi-graph.
VoxDet: Voxel Learning for Novel Instance Detection Bowen Li1 Jiashun Wang
By leveraging associated camera poses, these features are aggregated into a compact 3D template voxel.
Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization
Gradient Descent (GD) is a simple yet efficient baseline algorithm for solving nonconvex optimization problems.
InDefenseoftheUnitaryScalarization forDeepMulti-TaskLearning
While some workshowsthatmulti-task networkstrained viaunitary scalarization exhibit superior performance to independent per-task models [29, 35], others suggest the opposite [30, 54, 58]. However, SMTOs usually require access to per-task gradients either with respect to the shared parameters, or to the shared representation.