SCALING LARGE LEARNING PROBLEMS WITH HARD PARALLEL MIXTURES
نویسندگان
چکیده
منابع مشابه
Scaling Large Learning Problems with Hard Parallel Mixtures
A challenge for statistical learning is to deal with large data sets, e.g. in data mining. The training time of ordinary Support Vector Machines is at least quadratic, which raises a serious research challenge if we want to deal with data sets of millions of examples. We propose a “hard parallelizable mixture” methodology which yields significantly reduced training time through modularization a...
متن کاملSolving Hard Subgraph Problems in Parallel
We look at problems involving finding subgraphs in larger graphs, such as the maximum clique problem, the subgraph isomorphism problem, and the maximum common subgraph problem. We investigate variable and value ordering heuristics, different inference strategies, intelligent backtracking search (backjumping), and bitand thread-parallelism to exploit modern hardware.
متن کاملTowards Sound Fresh Re-keying with Hard (Physical) Learning Problems
Most leakage-resilient cryptographic constructions aim at limiting the information adversaries can obtain about secret keys. In the case of asymmetric algorithms, this is usually obtained by secret sharing (aka masking) the key, which is made easy by their algebraic properties. In the case of symmetric algorithms, it is rather key evolution that is exploited. While more efficient, the scope of ...
متن کاملEmbedding Hard Learning Problems Into Gaussian Space
We give the first representation-independent hardness result for agnostically learning halfspaces with respect to the Gaussian distribution. We reduce from the problem of learning sparse parities with noise with respect to the uniform distribution on the hypercube (sparse LPN), a notoriously hard problem in theoretical computer science and show that any algorithm for agnostically learning halfs...
متن کاملCryptographic Primitives Based on Hard Learning Problems
Modern cryptography has had considerable impact on the development of computational learning theory. Tools from cryptography have been used in proving nearly all of the strong negative results for learning. In this paper, we give results in the reverse direction by showing how to construct several cryptographic primitives based on certain assumptions on the di culty of learning. Thus we develop...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: International Journal of Pattern Recognition and Artificial Intelligence
سال: 2003
ISSN: 0218-0014,1793-6381
DOI: 10.1142/s0218001403002411