#### Filter Results:

- Full text PDF available (9)

#### Publication Year

1965

2017

- This year (3)
- Last 5 years (9)
- Last 10 years (10)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

Learn More

- Amr Sharaf, Marwan Torki, Mohamed E. Hussein, Motaz El-Saban
- 2015 IEEE Winter Conference on Applications of…
- 2015

In this paper we introduce a real-time system for action detection. The system uses a small set of robust features extracted from 3D skeleton data. Features are effectively described based on the probability distribution of skeleton data. The descriptor computes a pyramid of sample covariance matrices and mean vectors to encode the relationship between the… (More)

- Amr Sharaf, Mohamed E. Hussein, Mohamed A. Ismail
- BMVC
- 2015

Ranking is the central problem for many applications such as web search, recommendation systems, and visual comparison of images. In this paper, the multiple kernel learning framework is generalized for the learning to rank problem. This approach extends the existing learning to rank algorithms by considering multiple kernel learning and consequently… (More)

- Amr Sharaf
- 2017

We present BanditLOLS, an algorithm for learning to make joint predictions from bandit feedback. The learner repeatedly predicts a sequence of actions, corresponding to either a structured output or control behavior, and observes feedback for that single output and no others. To address this limited feedback, we design a structured cost-estimation strategy… (More)

- Amr Sharaf, Shi Feng, Khanh Nguyen, Kianté Brantley, Hal Daumé
- WMT
- 2017

We describe the University of Maryland machine translation systems submitted to the WMT17 German-English Bandit Learning Task. The task is to adapt a translation system to a new domain, using only bandit feedback: the system receives a German sentence to translate, produces an English sentence, and only gets a scalar score as feedback. Targeting these two… (More)

- Amr Sharaf, Liqian Zhang
- 2016

In the multi-arm bandit problem with iid rewards, the learner selects an arm a ∈ A at every time step t. Learning proceeds in rounds, and we assume that the number of rounds is fixed, and indexed by t = 1 · · ·T . At each round, the algorithm chooses one action at (we’ll use the arms and actions interchangeably to mean the same thing). After taking the… (More)

So far we’ve discussed non-adaptive exploration strategies. Now let’s talk about adaptive exploration, in a sense that the bandit feedback of different arms in previous rounds are fully utilized. Let’s start with 2 arms. One fairly natural idea is to alternate them until we find that one arm is much better than the other, at which time we abandon the… (More)

- Amr Sharaf, Hal Daumé
- SPNLP@EMNLP
- 2017

We present an algorithm for structured prediction under online bandit feedback. The learner repeatedly predicts a sequence of actions, generating a structured output. It then observes feedback for that output and no others. We consider two cases: a pure bandit setting in which it only observes a loss, and more fine-grained feedback in which it observes a… (More)

- Amr Sharaf, Mohamad Y. Mansour
- The Journal of the Egyptian Medical Association
- 1965

- Arti Nanda, Amr Sharaf, Qasem A Alsaleh
- Pediatric dermatology
- 2010

Oral-facial-digital syndrome type 1 (OMIM #311200) is an X-linked dominant, developmental disorder. Among the 13 described clinical variants of oral-facial-digital syndrome, oral-facial-digital syndrome type 1 is of significance to dermatologists due to presence of congenital milia and hypotrichosis, not described in other variants. Since… (More)

- Alex Slivkins, Amr Sharaf
- 2016

In this lecture, we will study bandit problems with linear costs. In this setting, actions are represented by vectors in a low-dimensional real space. For simplicity, we will assume that all actions lie within a unit hypercube: a ∈ [0, 1]d. The action costs ct(a) are linear in the vector a, namely: ct(a) = a · vt for some weight vector vt ∈ Rd which is the… (More)