Correction to "The Importance of Convexity in Learning With Squared Loss"

نویسندگان

  • Wee Sun Lee
  • Peter L. Bartlett
  • Robert C. Williamson
چکیده

The paper “The Importance of Convexity in Learning with Squared Loss” gave a lower bound on the sample complexity of learning with quadratic loss using a nonconvex function class. The proof contains an error. We show that the lower bound is true under a stronger condition that holds for many cases of interest.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Concept Revision of Age, Motivation, and Error Correction in Second Language Learning

The current review article investigates some variables contributing to English language teaching and learning. Three factors of age, motivation and error correction have been of importance in English language curricula in language centres. Some studies have been conducted to investigate various effects of these three components on English language acquisition, those studies, however, may lack d...

متن کامل

Estimating a Bounded Normal Mean Relative to Squared Error Loss Function

Let be a random sample from a normal distribution with unknown mean and known variance The usual estimator of the mean, i.e., sample mean is the maximum likelihood estimator which under squared error loss function is minimax and admissible estimator. In many practical situations, is known in advance to lie in an interval, say for some In this case, the maximum likelihood estimator...

متن کامل

Minimax Estimator of a Lower Bounded Parameter of a Discrete Distribution under a Squared Log Error Loss Function

The problem of estimating the parameter ?, when it is restricted to an interval of the form , in a class of discrete distributions, including Binomial Negative Binomial discrete Weibull and etc., is considered. We give necessary and sufficient conditions for which the Bayes estimator of with respect to a two points boundary supported prior is minimax under squared log error loss function....

متن کامل

Experienced and Novice Language Teachers’ Beliefs about Corrective Feedback

The present study attempts to uncover language teachers’ beliefs about oral corrective feedback. It also explores the role of teachers’ experiences in their choice of error correction techniques. To achieve the purpose of the study, 137 foreign language teachers were asked to fill out the developed questionnaire and follow-up interviewed were conducted with 10 teachers, five novice and experien...

متن کامل

Revenue Optimization with Approximate Bid Predictions

In the context of advertising auctions, finding good reserve prices is a notoriously challenging learning problem. This is due to the heterogeneity of ad opportunity types, and the non-convexity of the objective function. In this work, we show how to reduce reserve price optimization to the standard setting of prediction under squared loss, a well understood problem in the learning community. W...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • IEEE Trans. Information Theory

دوره 54  شماره 

صفحات  -

تاریخ انتشار 2008