Statistical Learning
Deep Anomaly Detection Using Geometric Transformations
Given a sample of images, all known to belong to a "normal"
Learning Temporal Point Processes via Reinforcement Learning
Shuang Li, Shuai Xiao, Shixiang Zhu, Nan Du, Yao Xie, Le Song
Social goods, such as healthcare, smart city, and information networks, often produce ordered event data in continuous time.
Smoothed Analysis of Discrete Tensor Decomposition and Assemblies of Neurons
Nima Anari, Constantinos Daskalakis, Wolfgang Maass, Christos Papadimitriou, Amin Saberi, Santosh Vempala
We analyze linear independence of rank one tensors produced by tensor powers of randomly perturbed vectors. This enables efficient decomposition of sums of high-order tensors. Our analysis builds upon Bhaskara et al.
Distributed Stochastic Optimization via Adaptive SGD
Ashok Cutkosky, Róbert Busa-Fekete
Stochastic convex optimization algorithms are the most popular way to train machine learning models on large-scale data.
Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Loss
Stephen Mussmann, Percy S. Liang
Neural Information Processing Systems http://nips.cc/
On the Convergence and Robustness of Training GANs with Regularized Optimal Transport
Maziar Sanjabi, Jimmy Ba, Meisam Razaviyayn, Jason D. Lee
Gaussian, to an unknown data distribution, which is only represented by empirical samples. In order to measure the mapping quality, various metrics between the probability distributions have been proposed.
Posterior Concentration for Sparse Deep Learning
Veronika Rockova, nicholas polson
Deep learning constructs are powerful tools for pattern matching and prediction.
Uniform Convergence of Gradients for Non-Convex Learning and Optimization
Dylan J. Foster, Ayush Sekhari, Karthik Sridharan
Our analysis follows the tradition of norm-based capacity control .
Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC
Tolga Birdal, Umut Simsekli, Mustafa Onur Eken, Slobodan Ilic
In this paper, we address the particular problem of initializing PGO, in which multiple local measurements are fused into a globally consistent estimate, without resorting to the costly bundle adjustment or optimization that uses structure.
Optimal Subsampling with Influence Functions
Neural Information Processing Systems http://nips.cc/