A Smooth Primal-Dual Optimization Framework for Nonsmooth Composite Convex Minimization

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Solving optimization problems is a key task for which quantum computers could possibly provide a speedup over the best known classical algorithms. Particular classes of optimization problems including semidefinite programming (SDP) and linear programming ( ...

This study experimentally validates robust designs for herringbone grooved journal bearings (HGJBs) in micro-turbocompressors, addressing manufacturing deviations that lead to rotor instabilities. Experiments on a Pelton-driven rotor system focused on maxi ...

Ensuring reliable operation in power grids given the complexity of modern electricity networks with increasing demands, varying generation and flows present significant computational challenges. Addressing these challenges, we develop efficient methods for ...

A comparison-based search algorithm lets a user find a target item t in a database by answering queries of the form, "Which of items i and j is closer to t?" Instead of formulating an explicit query (such as one or several keywords), the user navigates tow ...

This paper offers a new algorithm to efficiently optimize scheduling decisions for dial-a-ride problems (DARPs), including problem variants considering electric and autonomous vehicles (e-ADARPs). The scheduling heuristic, based on linear programming theor ...

Distributed learning is the key for enabling training of modern large-scale machine learning models, through parallelising the learning process. Collaborative learning is essential for learning from privacy-sensitive data that is distributed across various ...

Modern optimization is tasked with handling applications of increasingly large scale, chiefly due to the massive amounts of widely available data and the ever-growing reach of Machine Learning. Consequently, this area of research is under steady pressure t ...

We study ensembles of elastic rods that are tensioned by a small set of inextensible cables. The cables induce forces that deform the initially straight, but flexible rods into 3D space curves at equilibrium. Rods can be open or closed, knotted, and arrang ...

Communication-constrained algorithms for decentralized learning and optimization rely on the exchange of quantized signals coupled with local updates. In this context, differential quantization is an effective technique to mitigate the negative impact of q ...

Sample efficiency is a fundamental challenge in de novo molecular design. Ideally, molecular generative models should learn to satisfy a desired objective under minimal calls to oracles (computational property predictors). This problem becomes more apparen ...

This paper presents a novel distributed approach for solving AC power flow (PF) problems. The optimization problem is reformulated into a distributed form using a communication structure corresponding to a hypergraph, by which complex relationships between ...

This paper develops a fast algorithm for computing the equilibrium assignment with the perturbed utility route choice (PURC) model. Without compromise, this allows the significant advantages of the PURC model to be used in large-scale applications. We form ...

We develop new tools to study landscapes in nonconvex optimization. Given one optimization problem, we pair it with another by smoothly parametrizing the domain. This is either for practical purposes (e.g., to use smooth optimization algorithms with good g ...

Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms. In this paper, we study the statistical guarantees on the excess risk achieved by early-stopped unconstrain ...

This paper proposes a computational approach to form-find pin-jointed bar structures subjected to combinations of tension and compression forces. The generated equilibrium states can meet structural and geometrical constraints via gradient-based optimizati ...

The support vector machine (SVM) is a supervised learning algorithm that finds a maximum-margin linear classifier, often after mapping the data to a high-dimensional feature space via the kernel trick. Recent work has demonstrated that in certain sufficien ...

In this thesis, we study two closely related directions: robustness and generalization in modern deep learning. Deep learning models based on empirical risk minimization are known to be often non-robust to small, worst-case perturbations known as adversari ...

Collaborative learning algorithms, such as distributed SGD (or D-SGD), are prone to faulty machines that may deviate from their prescribed algorithm because of software or hardware bugs, poisoned data or malicious behaviors. While many solutions have been ...

This paper studies the problem of online performance optimization of constrained closed-loop control systems, where both the objective and the constraints are unknown black-box functions affected by exogenous time-varying contextual disturbances. A primal- ...

Cutting plane methods are a fundamental approach for solving integer linear programs (ILPs). In each iteration of such methods, additional linear constraints (cuts) are introduced to the constraint set with the aim of excluding the previous fractional opti ...

A Smooth Primal-Dual Optimization Framework for Nonsmooth Composite Convex Minimization

Chat with Graph Search

Slack-variable Approach for Variational Quantum Semidefinite Programming

Robust design optimization of gas-lubricated herringbone grooved journal bearings: Surrogate modeling and experimental validation

Multi-Period Optimal Power Flow: Convex Relaxations and Parallel Algorithms

Fast Interactive Search under a Scale-Free Comparison Oracle

A ride time-oriented scheduling algorithm for dial-a-ride problems

Optimization Algorithms for Decentralized, Distributed and Collaborative Machine Learning

Scalable constrained optimization

Tencers: Tension-Constrained Elastic Rods

Differential Error Feedback for Communication-Efficient Decentralized Optimization

Augmented Memory: Sample-Efficient Generative Molecular Design with Reinforcement Learning

Hypergraph-Based Fast Distributed AC Power Flow Optimization

Perturbed Utility Stochastic Traffic Assignment

The effect of smooth parametrizations on nonconvex optimization landscapes

The statistical complexity of early-stopped mirror descent

Constrained Form-Finding of Tension-Compression Structures using Automatic Differentiation

New Equivalences between Interpolation and SVMs: Kernels and Structured Features

Understanding generalization and robustness in modern deep learning

Robust Collaborative Learning with Linear Gradient Overhead

Primal-Dual Contextual Bayesian Optimization for Control System Online Optimization with Time-Average Constraints

Learning to Remove Cuts in Integer Linear Programming