#### Filter Results:

- Full text PDF available (8)

#### Publication Year

2013

2018

- This year (1)
- Last 5 years (13)
- Last 10 years (13)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

Learn More

- Jiwei Li, Will Monroe, Tianlin Shi, Alan Ritter, Daniel Jurafsky
- EMNLP
- 2017

In this paper, drawing intuition from the Turing test, we propose using adversarial training for open-domain dialogue generation: the system is trained to produce sequences that are indistinguishableâ€¦ (More)

- Chongxuan Li, Jun Zhu, Tianlin Shi, Bo Zhang
- NIPS
- 2015

Deep generative models (DGMs) are effective on learning multilayered representations of complex data and performing inference of input data by exploring the generative ability. However, little workâ€¦ (More)

- Tianlin Shi, Jun Zhu
- Journal of Machine Learning Research
- 2014

where the constant C = exp(ytÏ„tÎ¼t xt + 12Ï„ t xt xt) . Therefore, the distribution qt+1(w) = N (Î¼t + Ï„txt, I) and as a by-product, the normalization term Î“(Ï„t) = âˆš 2Ï€ K exp(Ï„tytx > t Î¼t + 1 2Ï„ 2 t x >â€¦ (More)

- Jian Li, Tianlin Shi
- Oper. Res. Lett.
- 2014

Given n independent integer-valued random variables X1, X2, . . . , Xn and an integer C , we study the fundamental problem of computing the probability that the sum X = X1+X2+Â· Â· Â·+Xn is at most C .â€¦ (More)

- Tianlin Shi, Jacob Steinhardt, Percy Liang
- AISTATS
- 2015

In structured prediction, most inference algorithms allocate a homogeneous amount of computation to all parts of the output, which can be wasteful when different parts vary widely in terms ofâ€¦ (More)

- Tianlin Shi, Ming Liang, Xiaolin Hu
- ArXiv
- 2014

- Tianlin Shi, Andrej Karpathy, Linxi Fan, Jonathan Hernandez, Percy Liang
- ICML
- 2017

While simulated game environments have greatly accelerated research in reinforcement learning, existing environments lack the open-domain realism of tasks in computer vision or natural languageâ€¦ (More)

- Tianlin Shi, Da Tang, Liwen Xu, Thomas Moscibroda
- UAI
- 2014

We consider the problem of recovering sparse correlated data on networks. To improve accuracy and reduce costs, it is strongly desirable to take the potentially useful side-information of networkâ€¦ (More)

- Evan Zheran Liu, Kelvin Guu, Panupong Pasupat, Tianlin Shi, Percy Liang
- ArXiv
- 2018

Reinforcement learning (RL) agents improve through trial-and-error, but when reward is sparse and the agent cannot discover successful action sequences, learning stagnates. This has been a notableâ€¦ (More)

- Tianlin Shi
- 2014

Information about the Institute for Interdisciplinary Information Sciences (IIIS) is typically acquired through the web pages, which is limited in its static nature. In this course project, weâ€¦ (More)