#### Filter Results:

- Full text PDF available (23)

#### Publication Year

2007

2019

- This year (7)
- Last 5 years (21)
- Last 10 years (32)

#### Supplemental Content

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Nicholas Ruozzi
- NIPS
- 2012

Sudderth, Wainwright, and Willsky conjectured that the Bethe approximation corresponding to any fixed point of the belief propagation algorithm over an attractive, pairwise binary graphical model… (More)

- Nicholas Ruozzi, Sekhar C. Tatikonda
- J. Mach. Learn. Res.
- 2012

Gaussian belief propagation (GaBP) is an iterative algorithm for computing the mean of a multivariate Gaussian distribution, or equivalently, the minimum of a multivariate positive definite quadratic… (More)

- Nicholas Ruozzi, Sekhar C. Tatikonda
- IEEE Transactions on Information Theory
- 2013

The max-product algorithm, a local message-passing scheme that attempts to compute the most probable assignment (MAP) of a given probability distribution, has been successfully employed as a method… (More)

- Nicholas Ruozzi, Sekhar Tatikonda
- UAI
- 2010

- Dexter Kozen, Nicholas Ruozzi
- CALCO
- 2007

Metric coinduction is a form of coinduction that can be used to establish properties of objects constructed as a limit of finite approximations. One can prove a coinduction step showing that some… (More)

- Nicholas Ruozzi, Justin Thaler, Sekhar C. Tatikonda
- 47th Annual Allerton Conference on Communication…
- 2009

We formulate a new approach to understanding the behavior of the min-sum algorithm by exploiting the properties of graph covers. First, we present a new, natural characterization of scaled diagonally… (More)

- Nicholas Ruozzi
- AISTATS
- 2017

Computing the partition function of an arbitrary graphical model is generally intractable. As a result, approximate inference techniques such as loopy belief propagation and expectation propagation… (More)

- Kui Tang, Nicholas Ruozzi, David Belanger, Tony Jebara
- AISTATS
- 2016

Many machine learning tasks require fitting probabilistic models over structured objects, such as pixel grids, matchings, and graph edges. Maximum likelihood estimation (MLE) for such domains is… (More)

- Nicholas Ruozzi, Sekhar C. Tatikonda
- 44th Annual Conference on Information Sciences…
- 2010

Gaussian belief propagation is an iterative algorithm for computing the mean of a multivariate Gaussian distribution. Equivalently, the min-sum algorithm can be used to compute the minimum of a… (More)

- Da Zhen Tang, Dawen Liang, Tony Jebara, Nicholas Ruozzi
- DGS@ICLR
- 2019

Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational… (More)