English
Related papers

Related papers: A Scalable and Extensible Framework for Superposit…

200 papers

Despite their dominance in vision and language, deep neural networks often underperform relative to tree-based models on tabular data. To bridge this gap, we incorporate five key inductive biases into deep learning: robustness to irrelevant…

Machine Learning · Statistics 2026-03-24 Kry Yik Chau Lui , Cheng Chi , Kishore Basu , Yanshuai Cao

In this paper, we propose new proximal Newton-type methods for convex optimization problems in composite form. The applications include model predictive control (MPC) and embedded MPC. Our new methods are computationally attractive since…

Optimization and Control · Mathematics 2020-07-21 Ilan Adler , Zhiyue Tom Hu , Tianyi Lin

Deepening and widening convolutional neural networks (CNNs) significantly increases the number of trainable weight parameters by adding more convolutional layers and feature maps per layer, respectively. By imposing inter- and intra-group…

Computer Vision and Pattern Recognition · Computer Science 2019-12-18 Kevin Bui , Fredrick Park , Shuai Zhang , Yingyong Qi , Jack Xin

We study the problem of estimating high-dimensional regression models regularized by a structured sparsity-inducing penalty that encodes prior structural information on either the input or output variables. We consider two widely adopted…

Machine Learning · Statistics 2012-07-02 Xi Chen , Qihang Lin , Seyoung Kim , Jaime G. Carbonell , Eric P. Xing

We present a framework to define a large class of neural networks for which, by construction, training by gradient flow provably reaches arbitrarily low loss when the number of parameters grows. Distinct from the fixed-space global…

Optimization and Control · Mathematics 2025-01-13 David A. R. Robin , Kevin Scaman , Marc Lelarge

We present a data dependent generalization bound for a large class of regularized algorithms which implement structured sparsity constraints. The bound can be applied to standard squared-norm regularization, the Lasso, the group Lasso, some…

Machine Learning · Computer Science 2012-08-21 Andreas Maurer , Massimiliano Pontil

In recent years, several models have improved the capacity to generate synthetic tabular datasets. However, such models focus on synthesizing simple columnar tables and are not useable on real-life data with complex structures. This paper…

Machine Learning · Computer Science 2022-02-07 Luca Canale , Nicolas Grislain , Grégoire Lothe , Johan Leduc

Inducing-point-based sparse variational Gaussian processes have become the standard workhorse for scaling up GP models. Recent advances show that these methods can be improved by introducing a diagonal scaling matrix to the conditional…

Machine Learning · Statistics 2025-07-04 Thang D. Bui , Michalis K. Titsias

The paper proposes and justifies a new algorithm of the proximal Newton type to solve a broad class of nonsmooth composite convex optimization problems without strong convexity assumptions. Based on advanced notions and techniques of…

Optimization and Control · Mathematics 2022-03-02 Boris S. Mordukhovich , Xiaoming Yuan , Shangzhi Zeng , Jin Zhang

Penalized linear regression is of fundamental importance in high-dimensional statistics and has been routinely used to regress a response on a high-dimensional set of predictors. In many scientific applications, there exists external…

Methodology · Statistics 2023-02-21 Sandipan Pramanik , Xianyang Zhang

This is an overview paper written in style of research proposal. In recent years we introduced a general framework for large-scale unconstrained optimization -- Sequential Subspace Optimization (SESOP) and demonstrated its usefulness for…

Numerical Analysis · Computer Science 2014-01-03 Michael Zibulevsky

Combining additive models and neural networks allows to broaden the scope of statistical regression and extend deep learning-based approaches by interpretable structured additive predictors at the same time. Existing attempts uniting the…

Machine Learning · Statistics 2022-07-12 David Rügamer , Chris Kolb , Nadja Klein

Supervised learning models, also known as quantitative structure-activity regression (QSAR) models, are increasingly used in assisting the process of preclinical, small molecule drug discovery. The models are trained on data consisting of a…

Applications · Statistics 2020-01-08 Oliver P Watson , Isidro Cortes-Ciriano , James A Watson

Optimization problems with composite functions consist of an objective function which is the sum of a smooth and a (convex) nonsmooth term. This particular structure is exploited by the class of proximal gradient methods and some of their…

Optimization and Control · Mathematics 2022-10-17 Christian Kanzow , Theresa Lechner

We consider stochastic second-order methods for minimizing smooth and strongly-convex functions under an interpolation condition satisfied by over-parameterized models. Under this condition, we show that the regularized subsampled Newton…

Machine Learning · Computer Science 2020-03-24 Si Yi Meng , Sharan Vaswani , Issam Laradji , Mark Schmidt , Simon Lacoste-Julien

The need for fast sparse optimization is emerging, e.g., to deal with large-dimensional data-driven problems and to track time-varying systems. In the framework of linear sparse optimization, the iterative shrinkage-thresholding algorithm…

Optimization and Control · Mathematics 2025-01-22 Vito Cerone , Sophie M. Fosson , Diego Regruto

Semi-structured networks (SSNs) merge the structures familiar from additive models with deep neural networks, allowing the modeling of interpretable partial feature effects while capturing higher-order non-linearities at the same time. A…

Machine Learning · Computer Science 2024-10-15 David Rügamer , Bernard X. W. Liew , Zainab Altai , Almond Stöcker

We provide a computational framework for approximating a class of structured matrices; here, the term structure is very general, and may refer to a regular sparsity pattern (e.g., block-banded), or be more highly structured (e.g., symmetric…

Numerical Analysis · Mathematics 2021-05-05 Misha E. Kilmer , Arvind K. Saibaba

We present two sampled quasi-Newton methods (sampled LBFGS and sampled LSR1) for solving empirical risk minimization problems that arise in machine learning. Contrary to the classical variants of these methods that sequentially build…

Optimization and Control · Mathematics 2021-07-29 Albert S. Berahas , Majid Jahani , Peter Richtárik , Martin Takáč

In this paper, we introduce a quasi-Newton method optimized for efficiently solving quasi-linear elliptic equations and systems, with a specific focus on GPU-based computation. By approximating the Jacobian matrix with a combination of…

Numerical Analysis · Mathematics 2025-03-25 Wenrui Hao , Sun Lee , Xiangxiong Zhang