{"title":"Concentration of measure","authors":"N. Berestycki, Richard Nickl","doi":"10.1017/9781108627771.003","DOIUrl":"https://doi.org/10.1017/9781108627771.003","url":null,"abstract":"The concentration of measure phenomenon was first put forward in the 70s and 80s in geometric functional analysis by Milman, Gromov, Schechtman, and has been subject to fascinating recent developments in probability theory, mostly due to M. Talagrand (1995, 1996ab) and M. Ledoux (2001). Very roughly speaking, this phenomenon can be stated in the following simple way: “a random variable that depends in a smooth way on many independent random variables (but not too much on any of them), is essentially constant.” Of course, the precise meaning of such a statement needs to be clarified, but often it will mean that the random variable X concentrates around a constant c in such a way that the probability of the event {|X − c| > t} is exponentially small in t. This type of bounds is usually referred to as a concentration inequality.","PeriodicalId":183443,"journal":{"name":"High-Dimensional Statistics","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132329251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Reproducing kernel Hilbert spaces","authors":"L. Rosasco","doi":"10.1017/9781108627771.012","DOIUrl":"https://doi.org/10.1017/9781108627771.012","url":null,"abstract":"In the previous two lectures, we’ve discussed the connections of the learning problem to statistical inference. However, unlike in traditional statistics, our primary goal with learning is to predict the future rather than describe the data at hand. We also typically have a much smaller sample of data in a much higher-dimensional space, so we cannot blindly choose a model and assume it will be accurate. If the model is too highly-parameterized, it will react too strongly to the data, we will overfit the data, and we will fail to learn the underlying phenomenon (see Figure 1 for an example of this behavior). However, models with too few parameters may not even describe the training data adequately, and will provide similarly bad performance. Regularization provides us with one way to strike the appropriate balance in creating our model. It requires a (possibly large) class of models and a method for evaluating the complexity of each model in the class. The concept of “kernels” will provide us with a flexible, computationally feasible method for implementing this scheme.","PeriodicalId":183443,"journal":{"name":"High-Dimensional Statistics","volume":"516 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133303876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Uniform laws of large numbers","authors":"C. C. Rodriguez","doi":"10.1007/0-387-22442-4_9","DOIUrl":"https://doi.org/10.1007/0-387-22442-4_9","url":null,"abstract":"","PeriodicalId":183443,"journal":{"name":"High-Dimensional Statistics","volume":"2020 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134264109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Principal component analysis in high dimensions","authors":"","doi":"10.1017/9781108627771.008","DOIUrl":"https://doi.org/10.1017/9781108627771.008","url":null,"abstract":"","PeriodicalId":183443,"journal":{"name":"High-Dimensional Statistics","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132013207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}