Entropy-based bounds for online algorithms
نویسندگان
چکیده
منابع مشابه
Online Bounds for Bayesian Algorithms
We present a competitive analysis of Bayesian learning algorithms in the online learning setting and show that many simple Bayesian algorithms (such as Gaussian linear regression and Bayesian logistic regression) perform favorably when compared, in retrospect, to the single best model in the model class. The analysis does not assume that the Bayesian algorithms’ modeling assumptions are “correc...
متن کاملLower Bounds for Online Algorithms
What is an oline problem Unlike the offline problems that we get the whole input at the beginning, in an online problem we just have some part of the input in advance. The rest of the input are queries that arrive one by one. Upon the arrival of each request, we need to process as it is received. In analyzing online algorithms, we usually, do not really care about the ruing time. The source of ...
متن کاملAlgorithms for Rigorous Entropy Bounds and Symbolic Dynamics
The aim of this paper is to introduce a method for computing rigorous lower bounds for topological entropy. The topological entropy of a dynamical system measures the number of trajectories that separate in finite time and quantifies the complexity of the system. Our method relies on extending existing computational Conley index techniques for constructing semi-conjugate symbolic dynamical syst...
متن کاملOnline Stochastic Matching: New Algorithms and Bounds
Online matching has received significant attention over the last 15 years due to its close connection to Internet advertising. As the seminal work of Karp, Vazirani, and Vazirani has an optimal (1 − 1/e) competitive ratio in the standard adversarial online model, much effort has gone into developing useful online models that incorporate some stochasticity in the arrival process. One such popula...
متن کاملGeneralization Bounds for Online Learning Algorithms with Pairwise Loss Functions
Efficient online learning with pairwise loss functions is a crucial component in building largescale learning system that maximizes the area under the Receiver Operator Characteristic (ROC) curve. In this paper we investigate the generalization performance of online learning algorithms with pairwise loss functions. We show that the existing proof techniques for generalization bounds of online a...
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: ACM Transactions on Algorithms
سال: 2007
ISSN: 1549-6325,1549-6333
DOI: 10.1145/1186810.1186817