Statistical Learning
Improved Algorithms for Neural Active Learning
We improve the theoretical and empirical performance of neural-network(NN)- based active learning algorithms for the non-parametric streaming setting.
Memory Efficient Meta-Learning with Large Images
Meta-learning approaches to few-shot classification are very computationally efficient.
A Related work
B.2 Hierarchical k -means for semantic identifier The pseudo code of hierarchical k -means is detailed in in Algorithm 1. Algorithm 1: Hierarchical k -means.
Pseudo-Spherical Contrastive Divergence
However, due to the intractable partition function, they are typically trained via contrastive divergence for maximum likelihood estimation.
Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks
We consider the task of minimizing the sum of smooth and strongly convex functions stored in a decentralized manner across the nodes of a communication network whose links are allowed to change in time.
Constrained Stochastic Nonconvex Optimization with State-dependent Markov Data Abhishek Roy
National Science Foundation (NSF) grant CCF-1934568.
Alleviating " Posterior Collapse " in Deep Topic Models via Policy Gradient Y ewen Li
However, the representation capability of existing deep topic models is still limited by the phenomenon of " posterior collapse ", which has been widely