中文
相关论文

相关论文: Towards A Deeper Geometric, Analytic and Algorithm…

200 篇论文

We aim at computing the derivative of the solution to a parametric optimization problem with respect to the involved parameters. For a class broader than that of strongly convex functions, this can be achieved by automatic differentiation…

最优化与控制 · 数学 2019-10-15 Sheheryar Mehmood , Peter Ochs

The numerical range of a matrix is studied geometrically via the cone of positive semidefinite matrices (or semidefinite cone for short). In particular it is shown that the feasible set of a two-dimensional linear matrix inequality (LMI),…

最优化与控制 · 数学 2010-04-08 Didier Henrion

The numerical range of a matrix is studied geometrically via the cone of positive semidefinite matrices (or semidefinite cone for short). In particular it is shown that the feasible set of a two-dimensional linear matrix inequality (LMI),…

最优化与控制 · 数学 2008-12-10 Didier Henrion

Many machine learning tasks, such as learning with invariance and policy evaluation in reinforcement learning, can be characterized as problems of learning from conditional distributions. In such problems, each sample $x$ itself is…

机器学习 · 计算机科学 2017-01-03 Bo Dai , Niao He , Yunpeng Pan , Byron Boots , Le Song

A sequential importance sampling algorithm is developed for the distribution that results when a matrix of independent, but not identically distributed, Bernoulli random variables is conditioned on a given sequence of row and column sums.…

统计计算 · 统计学 2013-01-18 Matthew T. Harrison , Jeffrey W. Miller

In this paper, we propose the Lipschitz margin ratio and a new metric learning framework for classification through maximizing the ratio. This framework enables the integration of both the inter-class margin and the intra-class dispersion,…

机器学习 · 计算机科学 2018-02-13 Mingzhi Dong , Xiaochen Yang , Yang Wu , Jing-Hao Xue

The research area of algorithms with predictions has seen recent success showing how to incorporate machine learning into algorithm design to improve performance when the predictions are correct, while retaining worst-case guarantees when…

机器学习 · 计算机科学 2022-12-06 Michael Dinitz , Sungjin Im , Thomas Lavastida , Benjamin Moseley , Sergei Vassilvitskii

Many fundamental questions in theoretical computer science are naturally expressed as special cases of the following problem: Let $G$ be a complex reductive group, let $V$ be a $G$-module, and let $v,w$ be elements of $V$. Determine if $w$…

代数几何 · 数学 2021-08-16 J. M. Landsberg

We examine gradient descent on unregularized logistic regression problems, with homogeneous linear predictors on linearly separable datasets. We show the predictor converges to the direction of the max-margin (hard margin SVM) solution. The…

机器学习 · 统计学 2024-10-29 Daniel Soudry , Elad Hoffer , Mor Shpigel Nacson , Suriya Gunasekar , Nathan Srebro

Algorithmic fairness involves expressing notions such as equity, or reasonable treatment, as quantifiable measures that a machine learning algorithm can optimise. Most work in the literature to date has focused on classification problems…

机器学习 · 计算机科学 2020-03-06 Daniel Steinberg , Alistair Reid , Simon O'Callaghan

As Basu (1977) writes, "Eliminating nuisance parameters from a model is universally recognized as a major problem of statistics," but after more than 50 years since Basu wrote these words, the two mainstream schools of thought in statistics…

统计方法学 · 统计学 2023-09-26 Ryan Martin

Adversarial training is a technique for training robust machine learning models. To encourage robustness, it iteratively computes adversarial examples for the model, and then re-trains on these examples via some update rule. This work…

机器学习 · 计算机科学 2019-05-23 Zachary Charles , Shashank Rajput , Stephen Wright , Dimitris Papailiopoulos

The probabilistic satisfiability of a logical expression is a fundamental concept known as the partition function in statistical physics and field theory, an evaluation of a related graph's Tutte polynomial in mathematics, and the…

离散数学 · 计算机科学 2022-06-09 Stephen Eubank , Madhurima Nath , Yihui Ren , Abhijin Adiga

We consider the structured-output prediction problem through probabilistic approaches and generalize the "perturb-and-MAP" framework to more challenging weighted Hamming losses, which are crucial in applications. While in principle our…

机器学习 · 统计学 2018-11-22 Tatiana Shpakova , Francis Bach , Anton Osokin

Meaningful comparison between sets of observations often necessitates alignment or registration between them, and the resulting optimization problems range in complexity from those admitting simple closed-form solutions to those requiring…

统计方法学 · 统计学 2025-10-08 Hajg Jasa , Ronny Bergmann , Christian Kümmerle , Avanti Athreya , Zachary Lubberts

As more researchers have become aware of and passionate about algorithmic fairness, there has been an explosion in papers laying out new metrics, suggesting algorithms to address issues, and calling attention to issues in existing…

We consider settings in which the distribution of a multivariate random variable is partly ambiguous. We assume the ambiguity lies on the level of the dependence structure, and that the marginal distributions are known. Furthermore, a…

数理金融 · 定量金融 2020-05-27 Stephan Eckstein , Michael Kupper , Mathias Pohl

This thesis studies two problems in modern statistics. First, we study selective inference, or inference for hypothesis that are chosen after looking at the data. The motiving application is inference for regression coefficients selected by…

机器学习 · 统计学 2015-07-02 Jason D. Lee

Despite the widespread use of machine learning algorithms to solve problems of technological, economic, and social relevance, provable guarantees on the performance of these data-driven algorithms are critically lacking, especially when the…

机器学习 · 计算机科学 2019-03-18 Abed AlRahman Al Makdah , Vaibhav Katewa , Fabio Pasqualetti

Efficiently learning mixture of Gaussians is a fundamental problem in statistics and learning theory. Given samples coming from a random one out of k Gaussian distributions in Rn, the learning problem asks to estimate the means and the…

机器学习 · 计算机科学 2015-03-11 Rong Ge , Qingqing Huang , Sham M. Kakade