Asia
Riemannian stochastic optimization methods avoid strict saddle points Anonymous Author(s) Affiliation Address email
Riemannian setting is a highly challenging affair.
Variational Learning on Aggregate Outputs with Gaussian Processes
Ho Chung Law, Dino Sejdinovic, Ewan Cameron, Tim Lucas, Seth Flaxman, Katherine Battle, Kenji Fukumizu
Neural Information Processing Systems http://nips.cc/
PerfectDou: DominatingDouDizhuwith PerfectInformationDistillation
As a challenging multi-player card game, DouDizhu has recently drawn much attention for analyzing competition and collaboration in imperfect-information games. In this paper, we propose PerfectDou, a state-of-the-art DouDizhu AI system that dominates the game, in an actor-critic framework with a proposed technique named perfect information distillation.
Discovery of Latent 3D Keypoints via End-to-end Geometric Reasoning
Supasorn Suwajanakorn, Noah Snavely, Jonathan J. Tompson, Mohammad Norouzi
Neural Information Processing Systems http://nips.cc/
Complexity Matters: Rethinking the Latent Space for Generative Modeling
Our investigation starts with the classic generative adversarial networks (GANs). Inspired by the GAN training objective, we propose a novel "distance" between the latent and data distributions, whose minimization
Multi-Agent Generative Adversarial Imitation Learning
Jiaming Song, Hongyu Ren, Dorsa Sadigh, Stefano Ermon
If the reward function does not cover all important aspects of the task, the agent could easily learn undesirable behaviors [4].
Chartalist: Labeled Graph Datasets for UTXO and Account-based Blockchains
However, analyzing blockchain data requires domain expertise and computational resources, which pose a significant barrier and hinder advancement in this field.