arXiv Statistics @arxiv_stats@qoto.org

Temporal Phenotyping using Deep Predictive Clustering of Disease Progression. (arXiv:2006.08600v1 [physics.med-ph]) http://arxiv.org/abs/2006.08600

On the training dynamics of deep networks with $L_2$ regularization. (arXiv:2006.08643v1 [stat.ML]) http://arxiv.org/abs/2006.08643

Variational Bayesian Monte Carlo with Noisy Likelihoods. (arXiv:2006.08655v1 [stat.ML]) http://arxiv.org/abs/2006.08655

Multiscale Deep Equilibrium Models. (arXiv:2006.08656v1 [cs.LG]) http://arxiv.org/abs/2006.08656

The Landscape of Nonconvex-Nonconcave Minimax Optimization. (arXiv:2006.08667v1 [math.OC]) http://arxiv.org/abs/2006.08667

On Adversarial Bias and the Robustness of Fair Machine Learning. (arXiv:2006.08669v1 [stat.ML]) http://arxiv.org/abs/2006.08669

To Pretrain or Not to Pretrain: Examining the Benefits of Pretraining on Resource Rich Tasks. (arXiv:2006.08671v1 [cs.CL]) http://arxiv.org/abs/2006.08671

Targeted Maximum Likelihood Estimation of Community-based Causal Effect of Community-Level Stochastic Interventions. (arXiv:2006.08675v1 [stat.AP]) http://arxiv.org/abs/2006.08675

Feature Space Saturation during Training. (arXiv:2006.08679v1 [cs.LG]) http://arxiv.org/abs/2006.08679

O(1) Communication for Distributed SGD through Two-Level Gradient Averaging. (arXiv:2006.07405v1 [cs.LG]) http://arxiv.org/abs/2006.07405

How to Avoid Being Eaten by a Grue: Structured Exploration Strategies for Textual Worlds. (arXiv:2006.07409v1 [cs.AI]) http://arxiv.org/abs/2006.07409

BI-MAML: Balanced Incremental Approach for Meta Learning. (arXiv:2006.07412v1 [cs.LG]) http://arxiv.org/abs/2006.07412

Manifold GPLVMs for discovering non-Euclidean latent structure in neural data. (arXiv:2006.07429v1 [stat.ML]) http://arxiv.org/abs/2006.07429

The Difficult Task of Distribution Generalization in Nonlinear Models. (arXiv:2006.07433v1 [stat.ME]) http://arxiv.org/abs/2006.07433

An Empirical Bayes Approach to Graphon Estimation. (arXiv:2006.07435v1 [stat.ME]) http://arxiv.org/abs/2006.07435

Attentive Feature Reuse for Multi Task Meta learning. (arXiv:2006.07438v1 [cs.LG]) http://arxiv.org/abs/2006.07438

Self-Imitation Learning via Generalized Lower Bound Q-learning. (arXiv:2006.07442v1 [cs.LG]) http://arxiv.org/abs/2006.07442

Fast Maximum Likelihood Estimation and Supervised Classification for the Beta-Liouville Multinomial. (arXiv:2006.07454v1 [stat.ML]) http://arxiv.org/abs/2006.07454

Detangling robustness in high dimensions: composite versus model-averaged estimation. (arXiv:2006.07457v1 [math.ST]) http://arxiv.org/abs/2006.07457

Towards Early Diagnosis of Epilepsy from EEG Data. (arXiv:2006.06675v1 [cs.LG]) http://arxiv.org/abs/2006.06675