Constructive Discrepancy Minimization with Hereditary L2 Guarantees
نویسنده
چکیده
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(ui)| and l2-discrepancy defined as disc2(S , χ) := √
منابع مشابه
Low Discrepancy Sequences and Learning
The Discrepancy Method is a constructive method for proving upper bounds that has received a lot of attention in recent years. In this paper we revisit a few important results, and show how it can be applied to problems in Machine Learning such as the Empirical Risk Minimization and Risk Estimation by exploiting connections with combinatorial dimension theory.
متن کاملDiscriminative State Space Models
We introduce and analyze Discriminative State-Space Models for forecasting nonstationary time series. We provide data-dependent generalization guarantees for learning these models based on the recently introduced notion of discrepancy. We provide an in-depth analysis of the complexity of such models. We also study the generalization guarantees for several structural risk minimization approaches...
متن کاملAdaptation Based on Generalized Discrepancy
We present a new algorithm for domain adaptation improving upon a discrepancy minimization algorithm, (DM), previously shown to outperform a number of algorithms for this problem. Unlike many previously proposed solutions for domain adaptation, our algorithm does not consist of a fixed reweighting of the losses over the training sample. Instead, the reweighting depends on the hypothesis sought....
متن کاملLecture Constructive Algorithms for Discrepancy Minimization
In terms of applications, the min discrepancy problem appears in many varied areas of both Computer Science (Computational Geometry, Comb. Optimization, Monte-Carlo simulation, Machine learning, Complexity, Pseudo-Randomness) and Mathematics (Dynamical Systems, Combinatorics, Mathematical Finance, Number Theory, Ramsey Theory, Algebra, Measure Theory,...). One may consult any of the following b...
متن کاملThe Gram-Schmidt Walk: A Cure for the Banaszczyk Blues
An important result in discrepancy due to Banaszczyk states that for any set of n vectors in R m of l2 norm at most 1 and any convex body K in R m of Gaussian measure at least half, there exists a ±1 combination of these vectors which lies in 5K. This result implies the best known bounds for several problems in discrepancy. Banaszczyk’s proof of this result is non-constructive and a major open ...
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:
- CoRR
دوره abs/1711.02860 شماره
صفحات -
تاریخ انتشار 2017