منابع مشابه
Bayesian representation learning with oracle constraints
Representation learning systems typically rely on massive amounts of labeled data in order to be trained to high accuracy. Recently, high-dimensional parametric models like neural networks have succeeded in building rich representations using either compressive, reconstructive or supervised criteria. However, the semantic structure inherent in observations is oftentimes lost in the process. Hum...
متن کاملStructural properties of oracle classes
Denote by C the class of oracles relative to which P = NP (collapsing oracles), and by S the class of oracles relative to which P 6= NP (separating oracles). We present structural results on C and S. Using a diagonalization argument, we show that neither C nor S is closed under disjoint union, also known as join. We show that this implies that neither C nor S is closed under union, intersection...
متن کاملThe Adaptive Lasso and Its Oracle Properties
The lasso is a popular technique for simultaneous estimation and variable selection. Lasso variable selection has been shown to be consistent under certain conditions. In this work we derive a necessary condition for the lasso variable selection to be consistent. Consequently, there exist certain scenarios where the lasso is inconsistent for variable selection. We then propose a new version of ...
متن کاملAn Oracle Inequality for Quasi-Bayesian Non-Negative Matrix Factorization
The aim of this paper is to provide some theoretical understanding of Bayesian non-negative matrix factorization methods. We derive an oracle inequality for a quasi-Bayesian estimator. This result holds for a very general class of prior distributions and shows how the prior affects the rate of convergence. We illustrate our theoretical results with a short numerical study along with a discussio...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Bayesian Analysis
سال: 2019
ISSN: 1936-0975
DOI: 10.1214/18-ba1097