Search Results for author:
Found 7 papers, 1 papers with code
From Estimation to Sampling for Bayesian Linear Regression with Spike-and-Slab Prior
We consider Bayesian linear regression with sparsity-inducing prior and design efficient sampling algorithms leveraging posterior contraction properties.
On the Dissipation of Ideal Hamiltonian Monte Carlo Sampler
We report on what seems to be an intriguing connection between variable integration time and partial velocity refreshment of Ideal Hamiltonian Monte Carlo samplers, both of which can be used for reducing the dissipative behavior of the dynamics.
Mirror Langevin Monte Carlo: the Case Under Isoperimetry
Motivated by the connection between sampling and optimization, we study a mirror descent analogue of Langevin dynamics and analyze three different discretization schemes, giving nonasymptotic convergence rate under functional inequalities such as Log-Sobolev in the corresponding metric.
Learning the Truth From Only One Side of the Story
Learning under one-sided feedback (i. e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems.
Optimizing Black-box Metrics with Adaptive Surrogates
We address the problem of training models with black-box and hard-to-optimize metrics by expressing the metric as a monotonic function of a small number of easy-to-optimize surrogates.
Complexity of Highly Parallel Non-Smooth Convex Optimization
Namely we consider optimization algorithms interacting with a highly parallel gradient oracle, that is one that can answer $\mathrm{poly}(d)$ gradient queries in parallel.
Subgradient Descent Learns Orthogonal Dictionaries
This paper concerns dictionary learning, i. e., sparse coding, a fundamental representation learning problem.
