Learning to Predict Combinatorial Structures
نویسندگان
چکیده
The major challenge in designing a discriminative learning algorithm for predicting structured data is to address the computational issues arising from the exponential size of the output space. Existing algorithms make different assumptions to ensure efficient, polynomial time estimation of model parameters. For several combinatorial structures, including cycles, partially ordered sets, permutations and other graph classes, these assumptions do not hold. In this thesis, we address the problem of designing learning algorithms for predicting combinatorial structures by introducing two new assumptions: (i) The first assumption is that a particular counting problem can be solved efficiently. The consequence is a generalisation of the classical ridge regression for structured prediction. (ii) The second assumption is that a particular sampling problem can be solved efficiently. The consequence is a new technique for designing and analysing probabilistic structured prediction models. These results can be applied to solve several complex learning problems including but not limited to multi-label classification, multi-category hierarchical classification, and label ranking.
منابع مشابه
Abstract: Learning to Predict Combinatorial Structures
Learning to Predict Combinatorial Structures Thomas Gärtner [email protected] Shankar Vembu [email protected] Fraunhofer IAIS, Schloß Birlinghoven, 53754 Sankt Augustin, Germany
متن کاملLearning to predict combinatorial structures
The major challenge in designing a discriminative learning algorithm for predicting structured data is to address the computational issues arising from the exponential size of the output space. Existing algorithms make different assumptions to ensure efficient, polynomial time estimation of model parameters. For several combinatorial structures, including cycles, partially ordered sets, permuta...
متن کاملSelf-Regulation, Goal Orientation, Tolerance of Ambiguity and Autonomy as Predictors of Iranian EFL learners’ Second Language Achievement: A Structural Equation Modeling Approach
The identification of the cognitive, affective, social and even physiological factors affecting second or foreign language learning routes and rate has for long been a challenging aspiration for second language researchers. However, a recent preoccupation of the researchers in this area has been the study of the combinatorial impacts of such factors on second or foreign language learning proces...
متن کاملAssessment of "drug-likeness" of a small library of natural products using chemoinformatics
Even though natural products has an excellent record as a source for new drugs, the advent of ultrahigh-throughput screening and large-scale combinatorial synthetic methods, has caused a decline in the use of natural products research in the pharmaceutical industry. This is due to the efficiency in generating and screening a high number of synthetic combinatorial compounds; whereas traditional ...
متن کاملHalf-Century Journey from Synthetic Organic Chemistry to Mathematical Stereochemistry through Chemoinformatics
My half-century journey started from synthetic organic chemistry. During the first stage of my journey, my interest in stereochemistry was initiated through the investigation on the participation of steric effects in reactive intermediates, cylophanes, strained heterocycles, and organic compounds for photography. In chemoinformatics as the next stage of the journey, I proposed the concept of im...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2010