Oceania
Understanding Benign Overfitting in Gradient-based Meta Learning
Meta learning has demonstrated tremendous success in few-shot learning with limited supervised data. In those settings, the meta model is usually overparameterized.
Structured Semidefinite Programming for Recovering Structured Preconditioners Arun Jambulapati Simons Institute
We develop a general framework for finding approximately-optimal preconditioners for solving linear systems.
Behavior From the Void: Unsupervised Active Pre-Training
We empirically evaluate APT by exposing task-specific reward after a long unsupervised pre-training phase.
Relative Flatness and Generalization
Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks.
Relative Flatness and Generalization
Flatness of the loss curve is conjectured to be connected to the generalization ability of machine learning models, in particular neural networks.
Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces Hung Tran-The
Traditionally, BO assumes that the search space is known. However, in many problems, this assumption does not hold.
ErrorCompensatedX: error compensation for variance reduced algorithms
Communication cost is one major bottleneck for the scalability for distributed learning.
Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
However, the simple power-law relation becomes more complicated when compute is considered.