English
Related papers

Related papers: Set structured global empirical risk minimizers ar…

200 papers

The effect of the relative entropy asymmetry is analyzed in the empirical risk minimization with relative entropy regularization (ERM-RER) problem. A novel regularization is introduced, coined Type-II regularization, that allows for…

Information Theory · Computer Science 2023-06-13 Francisco Daunas , Iñaki Esnaola , Samir M. Perlaza , H. Vincent Poor

The de-facto standard approach of promoting sparsity by means of $\ell_1$-regularization becomes ineffective in the presence of simplex constraints, i.e.,~the target is known to have non-negative entries summing up to a given constant. The…

Methodology · Statistics 2016-05-04 Ping Li , Syama Sundar Rangapuram , Martin Slawski

When building either prediction intervals for regression (with real-valued response) or prediction sets for classification (with categorical responses), uncertainty quantification is essential to studying complex machine learning methods.…

Machine Learning · Statistics 2022-06-17 Chen Xu , Yao Xie

We study mixed models with a single grouping factor, where inference about unknown parameters requires optimizing a marginal likelihood defined by an intractable integral. Low-dimensional numerical integration techniques are regularly used…

Methodology · Statistics 2025-01-22 Alex Stringer , Blair Bilodeau , Yanbo Tang

We consider rather general structural equation models (SEMs) between a target and its covariates in several shifted environments. Given $k\in\mathbb{N}$ shifts we consider the set of shifts that are at most $\gamma$-times as strong as a…

Statistics Theory · Mathematics 2024-07-31 Philip Kennerberg , Ernst C. Wit

Two typical fixed-length random number generation problems in information theory are considered for general sources. One is the source resolvability problem and the other is the intrinsic randomness problem. In each of these problems, the…

Information Theory · Computer Science 2024-05-14 Ryo Nomura , Hideki Yagi

Neural networks have dramatically increased our capacity to learn from large, high-dimensional datasets across innumerable disciplines. However, their decisions are not easily interpretable, their computational costs are high, and building…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Mackenzie J. Meni , Ryan T. White , Michael Mayo , Kevin Pilkiewicz

We consider robust empirical risk minimization (ERM), where model parameters are chosen to minimize the worst-case empirical loss when each data point varies over a given convex uncertainty set. In some simple cases, such problems can be…

Optimization and Control · Mathematics 2024-09-17 Eric Luxenberg , Dhruv Malik , Yuanzhi Li , Aarti Singh , Stephen Boyd

We study in this paper the consequences of using the Mean Absolute Percentage Error (MAPE) as a measure of quality for regression models. We show that finding the best model under the MAPE is equivalent to doing weighted Mean Absolute Error…

Machine Learning · Statistics 2015-09-09 Arnaud De Myttenaere , Bénédicte Le Grand , Fabrice Rossi

Many modern neural network architectures are trained in an overparameterized regime where the parameters of the model exceed the size of the training dataset. Sufficiently overparameterized neural network architectures in principle have the…

Machine Learning · Computer Science 2019-02-14 Samet Oymak , Mahdi Soltanolkotabi

We describe an approach to improving model fitting and model generalization that considers the entropy of distributions of modelling residuals. We use simple simulations to demonstrate the observational signatures of overfitting on ordered…

Methodology · Statistics 2019-08-05 Barnaby Rowe

We obtain sharp oracle inequalities for the empirical risk minimization procedure in the regression model under the assumption that the target Y and the model F are subgaussian. The bound we obtain is sharp in the minimax sense if F is…

Statistics Theory · Mathematics 2016-09-20 Guillaume Lecué , Shahar Mendelson

Efficient exploration is a central problem in reinforcement learning and is often formalized as maximizing the entropy of the state-action occupancy measure. While unconstrained maximum-entropy exploration is relatively well understood,…

Machine Learning · Computer Science 2026-05-01 Florian Wolf , Ilyas Fatkhullin , Niao He

In stochastic convex optimization the goal is to minimize a convex function $F(x) \doteq {\mathbf E}_{{\mathbf f}\sim D}[{\mathbf f}(x)]$ over a convex set $\cal K \subset {\mathbb R}^d$ where $D$ is some unknown distribution and each…

Machine Learning · Computer Science 2016-12-28 Vitaly Feldman

Symbolic regression is an important but challenging research topic in data mining. It can detect the underlying mathematical models. Genetic programming (GP) is one of the most popular methods for symbolic regression. However, its…

Data Structures and Algorithms · Computer Science 2017-05-16 Chen Chen , Changtong Luo , Zonglin Jiang

The pervasive presence spatial and size structure in biological populations challenges fundamental assumptions at the heart of continuum models of population dynamics based on mean densities (local or global) only. Individual-based models…

Populations and Evolution · Quantitative Biology 2012-02-29 Michael Raghib , Nicholas A. Hill , Ulf Dieckmann

Entropy is a measure of self-information which is used to quantify losses. Entropy was developed in thermodynamics, but is also used to compare probabilities based on their deviating information content. Corresponding model uncertainty is…

Probability · Mathematics 2018-01-23 Alois Pichler , Ruben Schlotter

Performative prediction is a framework accounting for the shift in the data distribution induced by the prediction of a model deployed in the real world. Ensuring rapid convergence to a stable solution where the data distribution remains…

Machine Learning · Computer Science 2026-01-30 Pedram Khorsandi , Rushil Gupta , Mehrnaz Mofakhami , Simon Lacoste-Julien , Gauthier Gidel

The entropic risk measure is widely used in high-stakes decision-making across economics, management science, finance, and safety-critical control systems because it captures tail risks associated with uncertain losses. However, when data…

Optimization and Control · Mathematics 2026-01-05 Utsav Sadana , Erick Delage , Angelos Georghiou

For random systems subject to a constraint, the microcanonical ensemble requires the constraint to be met by every realisation ("hard constraint"), while the canonical ensemble requires the constraint to be met only on average ("soft…

Probability · Mathematics 2021-12-08 Pierfrancesco Dionigi , Diego Garlaschelli , Frank den Hollander , Michel Mandjes
‹ Prev 1 4 5 6 7 8 10 Next ›