← Optimization & Theory
Machine Learning › Optimization & Theory ›

Stochastic Processes

2667 directly classified papers

Papers per year

Papers

Exploring $k$ out of Top $ρ$ Fraction of Arms in Stochastic Bandits AISTATS 2019
Sampling from Non-Log-Concave Distributions via Variance-Reduced Gradient Langevin Dynamics AISTATS 2019
Credit Assignment Techniques in Stochastic Computation Graphs AISTATS 2019
Learning Linear Dynamical Systems with Semi-Parametric Least Squares COLT 2019
The Randomized Midpoint Method for Log-Concave Sampling NIPS 2019
User-Specified Local Differential Privacy in Unconstrained Adaptive Online Learning NIPS 2019
Thinning for Accelerating the Learning of Point Processes NIPS 2019
Kalman Filter, Sensor Fusion, and Constrained Regression: Equivalences and Insights NIPS 2019
Estimating Convergence of Markov chains with L-Lag Couplings NIPS 2019
Accurate Layerwise Interpretable Competence Estimation NIPS 2019
Discovering Temporal Patterns from Insurance Interaction Data AAAI 2019
On the statistical rate of nonlinear recovery in generative models with heavy-tailed data ICML 2019
Graph Convolutional Gaussian Processes ICML 2019
Deep Gaussian Processes with Importance-Weighted Variational Inference ICML 2019
A Contrastive Divergence for Combining Variational Inference and MCMC ICML 2019
LF-PPL: A Low-Level First Order Probabilistic Programming Language for Non-Differentiable Models AISTATS 2019
Bayesian Functional Optimisation with Shape Prior AAAI 2019
Deep Exploration via Randomized Value Functions JMLR 2019
A Wrapped Normal Distribution on Hyperbolic Space for Gradient-Based Learning ICML 2019
New Convergence Aspects of Stochastic Gradient Algorithms JMLR 2019
Deep Optimal Stopping JMLR 2019
Understanding Persuasion Cascades in Online Product Rating Systems AAAI 2019
DeepSTN+: Context-Aware Spatial-Temporal Neural Network for Crowd Flow Prediction in Metropolis AAAI 2019
Learning Heterogeneous Spatial-Temporal Representation for Bike-Sharing Demand Prediction AAAI 2019
Log-concave sampling: Metropolis-Hastings algorithms are fast JMLR 2019