Computer Science and Artificial Intelligence Lab (CSAIL)
http://hdl.handle.net/1721.1/5458
Thu, 30 Jun 2016 15:35:12 GMT2016-06-30T15:35:12ZEvaluating Caching Mechanisms In Future Internet Architectures
http://hdl.handle.net/1721.1/103381
Evaluating Caching Mechanisms In Future Internet Architectures
Jing, Yuxin
This thesis seeks to test and evaluate the effects of in-network storage in novel proposed Internet architectures in terms of their performance. In a world where more and more people are mobile and connected to the Internet, we look at how the added variable of user mobility can affect how these architectures perform under different loads. Evaluating the effects of in-network storage and caching in these novel architectures will provide another facet to understanding how viable of an alternative they would be to the current TCP/IP paradigm of today's Internet. In Named Data Networking, where the storage is used to directly cache content, we see its use of storage impact the locality of where things are, while in MobilityFirst, where storage is used to cache chunks to provide robust delivery, we look at how its different layers work together in a mobility event.
MEng thesis
Tue, 28 Jun 2016 00:00:00 GMThttp://hdl.handle.net/1721.1/1033812016-06-28T00:00:00ZModeling Network User Behavior: Various Approaches
http://hdl.handle.net/1721.1/103379
Modeling Network User Behavior: Various Approaches
Xu, Shidan
This project involves learning to predict users' mobility within the network topology. Topological mobility, as opposed to physical mobility, can be substantial as a user switches from LTE to wifi network, while moving minimally physically. Our dataset consists of email IMAP logs as they document associated client IP addresses, as well as the clients' identifiers. Prediction for online mobility is of particular interest to the networks community. If we can predict online mobility with high probability, then new network architecture can be designed to optimize the caching system by minimizing resending packets. We used various approaches and techniques to model the user's behavior, including probabilistic programming, regression, neural nets, and clustering algorithms. We compare and contrast how models differ in their prediction accuracy, speed of convergence, and algorithmic complexity.
MEng thesis
Tue, 28 Jun 2016 00:00:00 GMThttp://hdl.handle.net/1721.1/1033792016-06-28T00:00:00ZTowards Practical Theory: Bayesian Optimization and Optimal Exploration
http://hdl.handle.net/1721.1/102796
Towards Practical Theory: Bayesian Optimization and Optimal Exploration
Kawaguchi, Kenji
This thesis discusses novel principles to improve the theoretical analyses of a class of methods, aiming to provide theoretically driven yet practically useful methods. The thesis focuses on a class of methods, called bound-based search, which includes several planning algorithms (e.g., the A* algorithm and the UCT algorithm), several optimization methods (e.g., Bayesian optimization and Lipschitz optimization), and some learning algorithms (e.g., PAC-MDP algorithms). For Bayesian optimization, this work solves an open problem and achieves an exponential convergence rate. For learning algorithms, this thesis proposes a new analysis framework, called PAC-RMDP, and improves the previous theoretical bounds. The PAC-RMDP framework also provides a unifying view of some previous near-Bayes optimal and PAC-MDP algorithms. All proposed algorithms derived on the basis of the new principles produced competitive results in our numerical experiments with standard benchmark tests.
SM thesis
Thu, 26 May 2016 00:00:00 GMThttp://hdl.handle.net/1721.1/1027962016-05-26T00:00:00ZDeep Learning without Poor Local Minima
http://hdl.handle.net/1721.1/102665
Deep Learning without Poor Local Minima
Kawaguchi, Kenji
In this paper, we prove a conjecture published in 1989 and also partially address an open problem announced at the Conference on Learning Theory (COLT) 2015. For an expected loss function of a deep nonlinear neural network, we prove the following statements under the independence assumption adopted from recent work: 1) the function is non-convex and non-concave, 2) every local minimum is a global minimum, 3) every critical point that is not a global minimum is a saddle point, and 4) the property of saddle points differs for shallow networks (with three layers) and deeper networks (with more than three layers). Moreover, we prove that the same four statements hold for deep linear neural networks with any depth, any widths and no unrealistic assumptions. As a result, we present an instance, for which we can answer to the following question: how difficult to directly train a deep model in theory? It is more difficult than the classical machine learning models (because of the non-convexity), but not too difficult (because of the nonexistence of poor local minima and the property of the saddle points). We note that even though we have advanced the theoretical foundations of deep learning, there is still a gap between theory and practice.
Mon, 23 May 2016 00:00:00 GMThttp://hdl.handle.net/1721.1/1026652016-05-23T00:00:00Z