English
Related papers

Related papers: A nested hierarchy of second order upper bounds on…

200 papers

We design an algorithm which finds an $\epsilon$-approximate stationary point (with $\|\nabla F(x)\|\le \epsilon$) using $O(\epsilon^{-3})$ stochastic gradient and Hessian-vector products, matching guarantees that were previously available…

Machine Learning · Computer Science 2020-06-25 Yossi Arjevani , Yair Carmon , John C. Duchi , Dylan J. Foster , Ayush Sekhari , Karthik Sridharan

Regularized risk minimization with the binary hinge loss and its variants lies at the heart of many machine learning problems. Bundle methods for regularized risk minimization (BMRM) and the closely related SVMStruct are considered the best…

Machine Learning · Computer Science 2009-09-09 Ankan Saha , Xinhua Zhang , S. V. N. Vishwanathan

Consider the problem of minimizing the sum of a smooth convex function and a separable nonsmooth convex function subject to linear coupling constraints. Problems of this form arise in many contemporary applications including signal…

Optimization and Control · Mathematics 2014-01-29 Mingyi Hong , Tsung-Hui Chang , Xiangfeng Wang , Meisam Razaviyayn , Shiqian Ma , Zhi-Quan Luo

In this work we update the bounds on $\sum m_{\nu}$ from latest publicly available cosmological data and likelihoods using Bayesian analysis, while explicitly considering particular neutrino mass hierarchies. In the minimal…

Cosmology and Nongalactic Astrophysics · Physics 2020-07-17 Shouvik Roy Choudhury , Steen Hannestad

This paper uses stochastic dominance principles to construct upper and lower sample path bounds for Hidden Markov Model (HMM) filters. Given a HMM, by using convex optimization methods for nuclear norm minimization with copositive…

Computation · Statistics 2015-06-22 Vikram Krishnamurthy , Cristian Rojas

We show that the algorithm to extract diverse M -solutions from a Conditional Random Field (called divMbest [1]) takes exactly the form of a Herding procedure [2], i.e. a deterministic dynamical system that produces a sequence of hypotheses…

Computer Vision and Pattern Recognition · Computer Science 2017-01-31 Ece Ozkan , Gemma Roig , Orcun Goksel , Xavier Boix

The Cauchy problem for the higher order equations in the mKdV hierarchy is investigated with data in the spaces $\hat{H}^r_s(\R)$ defined by the norm $$\n{v_0}{\hat{H}^r_s(\R)} := \n{< \xi > ^s\hat{v_0}}{L^{r'}_{\xi}},\quad < \xi…

Analysis of PDEs · Mathematics 2009-10-28 Axel Gruenrock

We consider the randomized decision tree complexity of the recursive 3-majority function. We prove a lower bound of $(1/2-\delta) \cdot 2.57143^h$ for the two-sided-error randomized decision tree complexity of evaluating height $h$ formulae…

Data Structures and Algorithms · Computer Science 2013-10-01 Frederic Magniez , Ashwin Nayak , Miklos Santha , Jonah Sherman , Gabor Tardos , David Xiao

We investigate the power of randomized algorithms for the maximum cardinality matching (MCM) and the maximum weight matching (MWM) problems in the online preemptive model. In this model, the edges of a graph are revealed one by one and the…

Data Structures and Algorithms · Computer Science 2015-07-03 Ashish Chiplunkar , Sumedh Tirodkar , Sundar Vishwanathan

The Bernstein-von Mises theorem (BvM) gives conditions under which the posterior distribution of a parameter $\theta\in\Theta\subseteq\mathbb R^d$ based on $n$ independent samples is asymptotically normal. In the high-dimensional regime, a…

Statistics Theory · Mathematics 2024-11-05 Anya Katsevich

The entropy accumulation theorem states that the smooth min-entropy of an $n$-partite system $A = (A_1, \ldots, A_n)$ is lower-bounded by the sum of the von Neumann entropies of suitably chosen conditional states up to corrections that are…

Quantum Physics · Physics 2019-07-23 Frédéric Dupuis , Omar Fawzi

Leveraging algorithmic stability to derive sharp generalization bounds is a classic and powerful approach in learning theory. Since Vapnik and Chervonenkis [1974] first formalized the idea for analyzing SVMs, it has been utilized to study…

Machine Learning · Computer Science 2021-01-26 Qinghua Liu , Zhou Lu

We consider the problem of binary classification with abstention in the relatively less studied \emph{bounded-rate} setting. We begin by obtaining a characterization of the Bayes optimal classifier for an arbitrary input-label distribution…

Machine Learning · Computer Science 2019-05-24 Shubhanshu Shekhar , Mohammad Ghavamzadeh , Tara Javidi

We consider the fundamental problem of selecting $k$ out of $n$ random variables in a way that the expected highest or second-highest value is maximized. This question captures several applications where we have uncertainty about the…

Computer Science and Game Theory · Computer Science 2020-12-16 Aranyak Mehta , Uri Nadav , Alexandros Psomas , Aviad Rubinstein

We present a new method to propagate lower bounds on conditional probability distributions in conventional Bayesian networks. Our method guarantees to provide outer approximations of the exact lower bounds. A key advantage is that we can…

Artificial Intelligence · Computer Science 2012-05-14 Daniel Andrade , Bernhard Sick

The trapping redundancy of a linear code is the number of rows of a smallest parity-check matrix such that no submatrix forms an $(a,b)$-trapping set. This concept was first introduced in the context of low-density parity-check (LDPC) codes…

Information Theory · Computer Science 2016-11-15 Yu Tsunoda , Yuichiro Fujiwara

We propose upper and lower bounds on the maximum success probability for discriminating given quantum states. The proposed upper bound is obtained from a suboptimal solution to the dual problem of the corresponding optimal state…

Quantum Physics · Physics 2018-01-12 Kenji Nakahira , Tsuyoshi Sasaki Usuda , Kentaro Kato

For the optimal success probability under minimum-error discrimination between $r\geq2$ arbitrary quantum states prepared with any a priori probabilities, we find new general analytical lower and upper bounds and specify the relations…

Quantum Physics · Physics 2022-03-07 Elena R. Loubenets

We present a novel approach to derive constraints on neutrino masses from cosmological data, while taking into account our ignorance of the neutrino mass ordering. We derive constraints from a combination of current and future cosmological…

Cosmology and Nongalactic Astrophysics · Physics 2018-02-02 Martina Gerbino , Massimiliano Lattanzi , Olga Mena , Katherine Freese

In principle, higher-order networks that have multiple edge types are more informative than their lower-order counterparts. In practice, however, excessively rich information may be algorithmically infeasible to extract. It requires an…

Social and Information Networks · Computer Science 2017-10-25 Tatsuro Kawamoto