Search Results for author:
Found 4 papers, 2 papers with code
Globally Optimal Training of Neural Networks with Threshold Activation Functions
We first show that regularized deep threshold network training problems can be equivalently formulated as a standard convex optimization problem, which parallels the LASSO method, provided that the last hidden layer width exceeds a certain threshold.
Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data
We show that the algorithm can detect the ground-truth pairs and improve performance by fully exploiting unpaired datasets.
Towards Sample-efficient Overparameterized Meta-learning
Specifically, for (1), we first show that learning the optimal representation coincides with the problem of designing a task-aware regularization to promote inductive bias.
Sample Efficient Subspace-based Representations for Nonlinear Meta-Learning
We prove that subspace-based representations can be learned in a sample-efficient manner and provably benefit future tasks in terms of sample complexity.
