Flexible Martingale Priors for Deep Hierarchies

نویسندگان

  • Jacob Steinhardt
  • Zoubin Ghahramani
چکیده

Figure 2: Trees drawn from the prior of the nCRP (top) and TSSB (bottom) models with N = 100 data points. In both cases we used a hyper-parameter of γ = 1. For TSSB, we further set α = 10 and λ = 2 (these are parameters that do not exist in the nCRP). Note that the tree generated by TSSB is very wide and shallow. A larger value of α would fix this for N = 100, but increasing N would cause the problem to re-appear.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Pathological Properties of Deep Bayesian Hierarchies

•All have the property that E[θn+1 | θn] = θn. •Called the martingale property •Philosophically desirable because it means that information is preserved as we move down the hierarchy •Theorem (Doob): All non-negative martingale sequences have a limit with probability 1. θn+1 | θn ∼ DP(cθn), θn+1 | θn ∼ BP(cθn), θn+1 | θn ∼ GammaP(cθn), θn+1 | θn ∼ PYP(cθn) Pathological Properties of Deep Bayesi...

متن کامل

Convex Point Estimation using Undirected Bayesian Transfer Hierarchies

When related learning tasks are naturally arranged in a hierarchy, an appealing approach for coping with scarcity of instances is that of transfer learning using a hierarchical Bayes framework. As fully Bayesian computations can be difficult and computationally demanding, it is often desirable to use posterior point estimates that facilitate (relatively) efficient prediction. However, the hiera...

متن کامل

Flexible Prior Distributions for Deep Generative Models

We consider the problem of training generative models with deep neural networks as generators, i.e. to map latent codes to data points. Whereas the dominant paradigm combines simple priors over codes with complex deterministic models, we argue that it might be advantageous to use more flexible code distributions. We demonstrate how these distributions can be induced directly from the data. The ...

متن کامل

SPRITE: Generalizing Topic Models with Structured Priors

We introduce SPRITE, a family of topic models that incorporates structure into model priors as a function of underlying components. The structured priors can be constrained to model topic hierarchies, factorizations, correlations, and supervision, allowing SPRITE to be tailored to particular settings. We demonstrate this flexibility by constructing a SPRITE-based model to jointly infer topic hi...

متن کامل

Optimal Stopping with Multiple Priors

We develop a theory of optimal stopping under Knightian uncertainty. A suitable martingale theory for multiple priors is derived in order to extend the classical dynamic programming or Snell envelope approach to multiple priors. We relate the multiple prior theory to the classical setup via a minimax theorem. In a multiple prior version of the classical i.i.d. model we discuss several examples ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2012