Country
Nearly tight sample complexity bounds for learning mixtures of Gaussians via sample compression schemes
Hassan Ashtiani, Shai Ben-David, Nicholas Harvey, Christopher Liaw, Abbas Mehrabian, Yaniv Plan
Formixtures of axis-aligned Gaussians, we show thateO(kd/ε2)samples suffice, matching a knownlowerbound.
Input-Output Equivalence of Unitary and Contractive RNNs
Melikasadat Emami, Mojtaba Sahraee Ardakan, Sundeep Rangan, Alyson K. Fletcher
Neural Information Processing Systems http://nips.cc/
Variational Structured Semantic Inference for Diverse Image Captioning
Fuhai Chen, Rongrong Ji, Jiayi Ji, Xiaoshuai Sun, Baochang Zhang, Xuri Ge, Yongjian Wu, Feiyue Huang, Yan Wang
Neural Information Processing Systems http://nips.cc/
A Statistical Recurrent Model on the Manifold of Symmetric Positive Definite Matrices
Rudrasis Chakraborty, Chun-Hao Yang, Xingjian Zhen, Monami Banerjee, Derek Archer, David Vaillancourt, Vikas Singh, Baba Vemuri
In a number of disciplines, the data (e.g., graphs, manifolds) to be analyzed are non-Euclideaninnature.
Cost
We then provide an algorithm to efficiently sketch input data using such embeddings. The sketch size of the embedding used in the algorithm has a linear dependence on the number of sketching dimensions of the input.
You Can't Counton Luck: Why Decision Transformersand RvS Failin Stochastic Environments
S is isasetofactions;T: S A S!