Search Results for author:
Found 10 papers, 6 papers with code
Large-Scale Gaussian Processes via Alternating Projection
Training and inference in Gaussian processes (GPs) require solving linear systems with $n\times n$ kernel matrices.
The Behavior and Convergence of Local Bayesian Optimization
A recent development in Bayesian optimization is the use of local optimization strategies, which can deliver strong empirical performance on high-dimensional problems compared to traditional global strategies.
On the Convergence of Black-Box Variational Inference
We provide the first convergence guarantee for full black-box variational inference (BBVI), also known as Monte Carlo variational inference.
Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference
Understanding the gradient variance of black-box variational inference (BBVI) is a crucial step for establishing its convergence and developing algorithmic improvements.
Local Bayesian optimization via maximizing probability of descent
Local optimization presents a promising approach to expensive, high-dimensional black-box optimization by sidestepping the need to globally explore the search space.
Discovering Many Diverse Solutions with Bayesian Optimization
Bayesian optimization (BO) is a popular approach for sample-efficient optimization of black-box objective functions.
Stronger and Faster Wasserstein Adversarial Attacks
While the majority of existing attacks focus on measuring perturbations under the $\ell_p$ metric, Wasserstein distance, which takes geometry in pixel space into account, has long been known to be a suitable metric for measuring image quality and has recently risen as a compelling alternative to the $\ell_p$ metric in adversarial attacks.
Newton-type Methods for Minimax Optimization
We prove their local convergence at strict local minimax points, which are surrogates of global solutions.
Understanding Adversarial Robustness: The Trade-off between Minimum and Average Margin
Deep models, while being extremely versatile and accurate, are vulnerable to adversarial attacks: slight perturbations that are imperceptible to humans can completely flip the prediction of deep models.
Distributional Reinforcement Learning for Efficient Exploration
In distributional reinforcement learning (RL), the estimated distribution of value function models both the parametric and intrinsic uncertainties.
