arXiv Statistics @arxiv_stats@qoto.org

Rethink Maximum Mean Discrepancy for Domain Adaptation. (arXiv:2007.00689v1 [cs.LG]) http://arxiv.org/abs/2007.00689

Accelerated Message Passing for Entropy-Regularized MAP Inference. (arXiv:2007.00699v1 [cs.LG]) http://arxiv.org/abs/2007.00699

Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search. (arXiv:2007.00708v1 [cs.LG]) http://arxiv.org/abs/2007.00708

Quantifying causal contribution via structure preserving interventions. (arXiv:2007.00714v1 [cs.AI]) http://arxiv.org/abs/2007.00714

Bayesian Coresets: An Optimization Perspective. (arXiv:2007.00715v1 [stat.ML]) http://arxiv.org/abs/2007.00715

Adaptive Discretization for Model-Based Reinforcement Learning. (arXiv:2007.00717v1 [cs.LG]) http://arxiv.org/abs/2007.00717

Adversarial Example Games. (arXiv:2007.00720v1 [cs.LG]) http://arxiv.org/abs/2007.00720

Sequential Transfer in Reinforcement Learning with a Generative Model. (arXiv:2007.00722v1 [cs.LG]) http://arxiv.org/abs/2007.00722

Scalable Monte Carlo Inference and Rescaled Local Asymptotic Normality. (arXiv:2007.00723v1 [math.ST]) http://arxiv.org/abs/2007.00723

Gradient Methods Never Overfit On Separable Data. (arXiv:2007.00028v1 [cs.LG]) http://arxiv.org/abs/2007.00028

Multi-way Graph Signal Processing on Tensors: Integrative analysis of irregular geometries. (arXiv:2007.00041v1 [eess.SP]) http://arxiv.org/abs/2007.00041

K-Nearest Neighbour and Support Vector Machine Hybrid Classification. (arXiv:2007.00045v1 [cs.CV]) http://arxiv.org/abs/2007.00045

Extracurricular Learning: Knowledge Transfer Beyond Empirical Distribution. (arXiv:2007.00051v1 [cs.LG]) http://arxiv.org/abs/2007.00051

Adversarial Mutual Information for Text Generation. (arXiv:2007.00067v1 [cs.CL]) http://arxiv.org/abs/2007.00067

Data Movement Is All You Need: A Case Study of Transformer Networks. (arXiv:2007.00072v1 [cs.LG]) http://arxiv.org/abs/2007.00072

Similarity Search for Efficient Active Learning and Search of Rare Concepts. (arXiv:2007.00077v1 [cs.LG]) http://arxiv.org/abs/2007.00077

Provably More Efficient Q-Learning in the Full-Feedback/One-Sided-Feedback Settings. (arXiv:2007.00080v1 [cs.LG]) http://arxiv.org/abs/2007.00080

Continuous-Time Multi-Armed Bandits with Controlled Restarts. (arXiv:2007.00081v1 [cs.LG]) http://arxiv.org/abs/2007.00081

Simple conditions for convergence of sequential Monte Carlo genealogies with applications. (arXiv:2007.00096v1 [stat.CO]) http://arxiv.org/abs/2007.00096

Filtering of stationary Gaussian statistical experiments. (arXiv:2006.16244v1 [math.ST]) http://arxiv.org/abs/2006.16244