English
Related papers

Related papers: Monotone Optimisation with Learned Projections

200 papers

The recovery of magnetic resonance (MR) images from undersampled measurements is a key problem that has seen extensive research in recent years. Unrolled approaches, which rely on end-to-end training of convolutional neural network (CNN)…

Image and Video Processing · Electrical Eng. & Systems 2023-12-04 Maneesh John , Jyothi Rikhab Chand , Mathews Jacob

Hyperparameter optimization (HPO) is increasingly used to automatically tune the predictive performance (e.g., accuracy) of machine learning models. However, in a plethora of real-world applications, accuracy is only one of the multiple --…

Machine Learning · Statistics 2021-06-25 Robin Schmucker , Michele Donini , Muhammad Bilal Zafar , David Salinas , Cédric Archambeau

This work aims to accelerate the convergence of proximal gradient methods used to solve regularized linear inverse problems. This is achieved by designing a polynomial-based preconditioner that targets the eigenvalue spectrum of the normal…

In this paper, we introduce two parabolic target-space interior-point algorithms for solving monotone linear complementarity problems. The first algorithm is based on a universal tangent direction, which has been recently proposed for…

Optimization and Control · Mathematics 2025-07-31 Marianna E. -Nagy , Tibor Illés , Yurii Nesterov , Petra Renáta Rigó

Low-Rank Adaptation (LoRA) enables efficient fine-tuning of large language models but suffers from catastrophic forgetting when learned updates interfere with the dominant singular directions that encode essential pre-trained knowledge. We…

Computation and Language · Computer Science 2025-11-11 Yifeng Xiong , Xiaohui Xie

This paper introduces an optimal control framework to address the inverse problem using a learned regularizer, with applications in image reconstruction. We build upon the concept of Learnable Optimization Algorithms (LOA), which combine…

Optimization and Control · Mathematics 2024-09-04 Wanyu Bian

Recently the field of inverse problems has seen a growing usage of mathematically only partially understood learned and non-learned priors. Based on first principles, we develop a projectional approach to inverse problems that addresses the…

Machine Learning · Computer Science 2019-08-07 Sören Dittmer , Peter Maass

In this short note, we reduce lower bounds on monotone projections of polynomials to lower bounds on extended formulations of polytopes. Applying our reduction to the seminal extended formulation lower bounds of Fiorini, Massar, Pokutta,…

Computational Complexity · Computer Science 2018-06-11 Joshua A. Grochow

We propose an algorithm for a family of optimization problems where the objective can be decomposed as a sum of functions with monotonicity properties. The motivating problem is optimization of hyperparameters of machine learning…

Machine Learning · Computer Science 2018-02-20 Wenyi Wang , William J. Welch

In inverse reinforcement learning (IRL), a learning agent infers a reward function encoding the underlying task using demonstrations from experts. However, many existing IRL techniques make the often unrealistic assumption that the agent…

Machine Learning · Computer Science 2023-01-04 Franck Djeumou , Christian Ellis , Murat Cubuktepe , Craig Lennon , Ufuk Topcu

In many practical applications, heuristic or approximation algorithms are used to efficiently solve the task at hand. However their solutions frequently do not satisfy natural monotonicity properties of optimal solutions. In this work we…

Machine Learning · Computer Science 2020-03-24 Evangelia Gergatsouli , Brendan Lucier , Christos Tzamos

The emerging generation of radio-interferometric (RI) arrays are set to form images of the sky with a new regime of sensitivity and resolution. This implies a significant increase in visibility data volumes, which for single-frequency…

Instrumentation and Methods for Astrophysics · Physics 2025-12-04 Olivier Leblanc , Chung San Chu , Laurent Jacques , Yves Wiaux

Large language models (LLMs) are increasingly deployed in real-world applications that require careful balancing of multiple, often conflicting, objectives, such as informativeness versus conciseness, or helpfulness versus creativity.…

Machine Learning · Computer Science 2025-08-12 Qiang He , Setareh Maghsudi

Multi-objective optimization (MOO) problems are prevalent in machine learning. These problems have a set of optimal solutions, called the Pareto front, where each point on the front represents a different trade-off between possibly…

Machine Learning · Computer Science 2021-04-27 Aviv Navon , Aviv Shamsian , Gal Chechik , Ethan Fetaya

We study the problem of learning a partially observed matrix under the low rank assumption in the presence of fully observed side information that depends linearly on the true underlying matrix. This problem consists of an important…

Machine Learning · Statistics 2026-02-05 Dimitris Bertsimas , Nicholas A. G. Johnson

Proximal policy optimization (PPO) is a widely-used algorithm for on-policy reinforcement learning. This work offers an alternative perspective of PPO, in which it is decomposed into the inner-loop estimation of update vectors, and the…

Machine Learning · Computer Science 2024-11-04 Charlie B. Tan , Edan Toledo , Benjamin Ellis , Jakob N. Foerster , Ferenc Huszár

Bayesian Optimization (BO) is a popular approach to optimizing expensive-to-evaluate black-box functions. Despite the success of BO, its performance may decrease exponentially as the dimensionality increases. A common framework to tackle…

Machine Learning · Computer Science 2024-12-24 Quoc-Anh Hoang Nguyen , The Hung Tran

In this paper, we investigate optimization problems with nonnegative and orthogonal constraints, where any feasible matrix of size $n \times p$ exhibits a sparsity pattern such that each row accommodates at most one nonzero entry. Our…

Optimization and Control · Mathematics 2025-11-06 Lei Wang , Xin Liu , Xiaojun Chen

Hyperparameter optimization (HPO) is important to leverage the full potential of machine learning (ML). In practice, users are often interested in multi-objective (MO) problems, i.e., optimizing potentially conflicting objectives, like…

Machine Learning · Computer Science 2024-01-12 Joseph Giovanelli , Alexander Tornede , Tanja Tornede , Marius Lindauer

We give a simple, fast algorithm for hyperparameter optimization inspired by techniques from the analysis of Boolean functions. We focus on the high-dimensional regime where the canonical example is training a neural network with a large…

Machine Learning · Computer Science 2018-01-23 Elad Hazan , Adam Klivans , Yang Yuan
‹ Prev 1 3 4 5 6 7 10 Next ›