Fast greedy $$\mathcal {C}$$-bound minimization with guarantees
نویسندگان
چکیده
منابع مشابه
Fast, Greedy Model Minimization for Unsupervised Tagging
Model minimization has been shown to work well for the task of unsupervised part-of-speech tagging with a dictionary. In (Ravi and Knight, 2009), the authors invoke an integer programming (IP) solver to do model minimization. However, solving this problem exactly using an integer programming formulation is intractable for practical purposes. We propose a novel two-stage greedy approximation sch...
متن کاملFast Greedy Searching Informative Genes via Redundancy Bound Bootstrapping
The identification of informative genes is very important in study of genomics. This task can be interpreted as searching a subset of genes such that an optimal “ratio of quality to price” is achieved. The “quality” refers to the discrimination power of genes and the “price” means the redundancy involved. This problem is NP hard. In contrast to many other methods, we discretize the gene express...
متن کاملConstructive Discrepancy Minimization with Hereditary L2 Guarantees
In discrepancy minimization problems, we are given a family of sets S = {S1, . . . , Sm}, with each Si ∈ S a subset of some universe U = {u1, . . . , un} of n elements. The goal is to find a coloring χ : U → {−1,+1} of the elements of U such that each set S ∈ S is colored as evenly as possible. Two classic measures of discrepancy are l∞-discrepancy defined as disc∞(S , χ) := maxS∈S | ∑ ui∈S χ(u...
متن کاملA Column Generation Bound Minimization Approach with PAC-Bayesian Generalization Guarantees
The C-bound, introduced in Lacasse et al. [2006], gives a tight upper bound on the risk of the majority vote classifier. Laviolette et al. [2011] designed a learning algorithm named MinCq that outputs a dense distribution on a finite set of base classifiers by minimizing the C-bound, together with a PACBayesian generalization guarantee. In this work, we design a column generation algorithm that...
متن کامل$\mathcal C$-graph automatic groups
We generalize the notion of a graph automatic group introduced by Kharlampovich, Khoussainov and Miasnikov by replacing the regular languages in their definition with more powerful language classes. For a fixed language class C, we call the resulting groups C-graph automatic. We prove that the class of C-graph automatic groups is closed under change of generating set, direct and free product fo...
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: Machine Learning
سال: 2020
ISSN: 0885-6125,1573-0565
DOI: 10.1007/s10994-020-05902-7