English
Related papers

Related papers: Risk Bounds and Calibration for a Smart Predict-th…

200 papers

This paper studies a structured compound stochastic program (SP) involving multiple expectations coupled by nonconvex and nonsmooth functions. We present a successive convex-programming based sampling algorithm and establish its…

Optimization and Control · Mathematics 2021-05-25 Junyi Liu , Ying Cui , Jong-Shi Pang

Proximal Policy Optimization (PPO) methods learn a policy by iteratively performing multiple mini-batch optimization epochs of a surrogate objective with one set of sampled data. Ratio clipping PPO is a popular variant that clips the…

Machine Learning · Computer Science 2022-02-02 Mingfei Sun , Vitaly Kurin , Guoqing Liu , Sam Devlin , Tao Qin , Katja Hofmann , Shimon Whiteson

Underdetermined or ill-posed inverse problems require additional information for \ldd{d} sound solutions with tractable optimization algorithms. Sparsity yields consequent heuristics to that matter, with numerous applications in signal…

Optimization and Control · Mathematics 2020-11-04 Afef Cherni , Emilie Chouzenoux , Laurent Duval , Jean-Christophe Pesquet

Adversarial robustness is an increasingly critical property of classifiers in applications. The design of robust algorithms relies on surrogate losses since the optimization of the adversarial loss with most hypothesis sets is NP-hard. But…

Machine Learning · Computer Science 2021-05-05 Pranjal Awasthi , Natalie Frank , Anqi Mao , Mehryar Mohri , Yutao Zhong

Stochastic gradient descent (SGD) is perhaps the most prevalent optimization method in modern machine learning. Contrary to the empirical practice of sampling from the datasets without replacement and with (possible) reshuffling at each…

Optimization and Control · Mathematics 2024-02-08 Xufeng Cai , Cheuk Yin Lin , Jelena Diakonikolas

The choice of loss function in classification involves a fundamental trade-off: smooth losses (like Cross-Entropy) enable fast optimization rates but yield slow square-root consistency bounds, while piecewise-linear losses (like Hinge)…

Machine Learning · Computer Science 2026-05-01 Mehryar Mohri , Yutao Zhong

In classification, the de facto method for aggregating individual losses is the average loss. When the actual metric of interest is 0-1 loss, it is common to minimize the average surrogate loss for some well-behaved (e.g. convex) surrogate.…

Machine Learning · Computer Science 2018-11-06 Bryan He , James Zou

The Lasso is a computationally efficient regression regularization procedure that can produce sparse estimators when the number of predictors (p) is large. Oracle inequalities provide probability loss bounds for the Lasso estimator at a…

Machine Learning · Statistics 2017-07-21 Cheryl J. Flynn , Clifford M. Hurvich , Jeffrey S. Simonoff

We establish upper bounds for the expected excess risk of models trained by proper iterative algorithms which approximate the local minima. Unlike the results built upon the strong globally strongly convexity or global growth conditions…

Machine Learning · Computer Science 2022-10-11 Mingyang Yi , Ruoyu Wang , Zhi-Ming Ma

We consider the problem of nonparametric estimation of a convex regression function $\phi_0$. We study the risk of the least squares estimator (LSE) under the natural squared error loss. We show that the risk is always bounded from above by…

Statistics Theory · Mathematics 2014-12-10 Adityanand Guntuboyina , Bodhisattva Sen

The predict+optimize problem combines machine learning ofproblem coefficients with a combinatorial optimization prob-lem that uses the predicted coefficients. While this problemcan be solved in two separate stages, it is better to…

Machine Learning · Computer Science 2020-12-07 Ali Ugur Guler , Emir Demirovic , Jeffrey Chan , James Bailey , Christopher Leckie , Peter J. Stuckey

In this work we provide a theoretical framework for structured prediction that generalizes the existing theory of surrogate methods for binary and multiclass classification based on estimating conditional probabilities with smooth convex…

Machine Learning · Computer Science 2019-02-14 Alex Nowak-Vila , Francis Bach , Alessandro Rudi

The need to rapidly solve PDEs in engineering design workflows has spurred the rise of neural surrogate models. In particular, neural operator models provide a discretization-invariant surrogate by retaining the infinite-dimensional,…

Machine Learning · Computer Science 2026-02-12 Yash Patel , Ambuj Tewari

Learning with non-modular losses is an important problem when sets of predictions are made simultaneously. The main tools for constructing convex surrogate loss functions for set prediction are margin rescaling and slack rescaling. In this…

Machine Learning · Statistics 2017-05-16 Jiaqian Yu , Matthew Blaschko

We propose a new stochastic optimization framework for empirical risk minimization problems such as those that arise in machine learning. The traditional approaches, such as (mini-batch) stochastic gradient descent (SGD), utilize an…

Machine Learning · Statistics 2020-02-04 Kenji Kawaguchi , Haihao Lu

Many real-world decision problems require solving, again and again, combinatorial optimization instances drawn from a common distribution. A recent line of structured learning methods exploits this regularity by learning policies that pair…

Machine Learning · Statistics 2026-05-20 Pierre-Cyril Aubin-Frankowski , Yohann De Castro , Axel Parmentier , Alessandro Rudi

We consider an online binary prediction setting where a forecaster observes a sequence of $T$ bits one by one. Before each bit is revealed, the forecaster predicts the probability that the bit is $1$. The forecaster is called…

Machine Learning · Computer Science 2023-10-09 Mingda Qiao , Gregory Valiant

This paper considers global optimization with a black-box unknown objective function that can be non-convex and non-differentiable. Such a difficult optimization problem arises in many real-world applications, such as parameter tuning in…

Optimization and Control · Mathematics 2016-07-19 Kenji Kawaguchi , Yu Maruyama , Xiaoyu Zheng

Enabling machine learning classifiers to defer their decision to a downstream expert when the expert is more accurate will ensure improved safety and performance. This objective can be achieved with the learning-to-defer framework which…

Machine Learning · Computer Science 2023-11-03 Yuzhou Cao , Hussein Mozannar , Lei Feng , Hongxin Wei , Bo An

We identify and analyze a fundamental limitation of the classical projected subgradient method in nonsmooth convex optimization: the inevitable failure caused by the absence of valid subgradients at boundary points. We show that, under…

Optimization and Control · Mathematics 2026-02-17 Zhihan Zhu , Yanhao Zhang , Yong Xia