#### Filter Results:

- Full text PDF available (5)

#### Publication Year

2013

2019

- This year (2)
- Last 5 years (10)
- Last 10 years (11)

#### Publication Type

#### Co-author

#### Journals and Conferences

Learn More

- Song Mei, Andrea Montanari, Phan-Minh Nguyen
- Proceedings of the National Academy of Sciences…
- 2018

Multilayer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding. Learning a neural network requires… (More)

- Dor Shaviv, Phan-Minh Nguyen, Ayfer Özgür
- IEEE International Symposium on Information…
- 2015

We consider an energy harvesting channel, in which the transmitter is powered by an exogenous stochastic energy arrival process, which can be stored in a battery of finite size. We provide an… (More)

- Dor Shaviv, Phan-Minh Nguyen, Ayfer Özgür
- IEEE International Symposium on Information…
- 2015

We consider an energy harvesting channel, in which the transmitter is powered by an exogenous stochastic energy arrival process, which can be stored in a battery of finite size. We provide an… (More)

- Raphaël Berthier, Andrea Montanari, Phan-Minh Nguyen
- ArXiv
- 2017

Given a high-dimensional data matrix ${\boldsymbol A}\in{\mathbb R}^{m\times n}$, Approximate Message Passing (AMP) algorithms construct sequences of vectors ${\boldsymbol u}^t\in{\mathbb R}^n$,… (More)

- Phan-Minh Nguyen, Marc André Armand, Tong Wu
- IEEE Communications Letters
- 2013

The Davey-MacKay coding scheme for channels with insertion, deletion and substitution errors exploits the use of a watermark string, known to both the encoder and the decoder, to regain… (More)

- Phan-Minh Nguyen
- ArXiv
- 2019

Can multilayer neural networks -- typically constructed as highly complex structures with many nonlinearly activated neurons across layers -- behave in a non-trivial way that yet simplifies away a… (More)

- Ping Li, Phan-Minh Nguyen
- ICLR
- 2019

We study the behavior of weight-tied multilayer vanilla autoencoders under the assumption of random weights. Via an exact characterization in the limit of large dimensions, our analysis reveals… (More)

- Andrea Montanari, Phan-Minh Nguyen
- IEEE International Symposium on Information…
- 2017

We consider the problem of reconstructing a vector x<inf>0</inf> ∊ R<sup>n</sup> from noisy linear observations y = Ax<inf>o</inf> + w, where A ∊ R<sup>m×n</sup> is a known operator and w is a noise… (More)

- Phan-Minh Nguyen, Marc André Armand
- IEEE Transactions on Information Theory
- 2015

In this correspondence, we illustrate among other things the use of the stationarity property of the set of capacity-achieving inputs in capacity calculations. In particular, as a case study, we… (More)

- Dor Shaviv, Phan-Minh Nguyen, Ayfer Özgür
- IEEE Transactions on Information Theory
- 2015

We consider an energy harvesting channel, in which the transmitter is powered by an exogenous stochastic energy harvesting process Et, such that 0 ≤ Et ≤ E̅, which can be stored in a battery of… (More)