Error Analysis of ERM Algorithm with Unbounded and Non-Identical Sampling
نویسندگان
چکیده
A standard assumption in the literature of learning theory is the samples which are drawn independently from an identical distribution with a uniform bounded output. This excludes the common case with Gaussian distribution. In this paper we extend these assumptions to a general case. To be precise, samples are drawn from a sequence of unbounded and non-identical probability distributions. By drift error analysis and Bennett inequality for the unbounded random variables, we derive a satisfactory learning rate for the ERM algorithm.
منابع مشابه
An Efficient Bi-objective Genetic Algorithm for the Single Batch-Processing Machine Scheduling Problem with Sequence Dependent Family Setup Time and Non-identical Job Sizes
This paper considers the problem of minimizing make-span and maximum tardiness simultaneously for scheduling jobs under non-identical job sizes, dynamic job arrivals, incompatible job families,and sequence-dependentfamily setup time on the single batch- processor, where split size of jobs is allowed between batches. At first, a new Mixed Integer Linear Programming (MILP) model is proposed for t...
متن کاملUpper and Lower Error Bounds for Active Learning
This paper analyzes the potential advantages and theoretical challenges of ”active learning” algorithms. Active learning involves sequential, adaptive sampling procedures that use information gleaned from previous samples in order to focus the sampling and accelerate the learning process relative to “passive learning” algorithms, which are based on non-adaptive (usually random) samples. There a...
متن کاملConcentration estimates for learning with unbounded sampling
We consider the least-square regularization schemes for regression problems in reproducing kernel Hilbert spaces. The learning algorithm is implemented with samples drawn from unbounded sampling processes. The purpose of this talk is to present concentration estimates for the error based on 2-empirical covering numbers, which improves learning rates in the literature.
متن کاملUltimate Tendon Stress in CFRP Strengthened Unbounded HSC Post-Tensioned Continuous I-Beams
The use of unbounded tendons is common in prestressed concrete structures and evaluation of the stress increase in unbonded tendons at ultimate flexural strength of such structure has posed a great challenge over the years. Based on the bending experiment for two-span continuous post-tension beams with unbounded tendons and externally applied CFRP sheets, the monitoring of the stress increment ...
متن کاملA new method to determine a well-dispersed subsets of non-dominated vectors for MOMILP problem
Multi-objective optimization is the simultaneous consideration of two or more objective functions that are completely or partially inconflict with each other. The optimality of such optimizations is largely defined through the Pareto optimality. Multiple objective integer linear programs (MOILP) are special cases of multiple criteria decision making problems. Numerous algorithms have been desig...
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 2016