Program for stream Advances in large scale nonlinear optimization

MA-32: Large Scale Constrained Optimization: Algorithms and Applications
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Matteo Lapucci, Marianna De Santis

• Feature selection in linear SVMs: a scalable SDP decomposition approach using a hard cardinality constraint
  Bo Peng, Immanuel Bomze, Laura Palagi
• A branch-and-cut algorithm for biclustering via semidefinite programming
  Antonio M. Sudoso
• Combining interior and exterior penalty for nonlinear costrained black-box optimization problems
  Andrea Brilli, Everton Silva, Ana Luisa Custodio, Giampaolo Liuzzi
• Estimation of Hydraulic Parameters Using the Augmented Lagrange Method
  Fabio Fortunato Filho, José Mario Martínez

MA-34: Optimization and learning for data science and imaging (Part I)
Stream: Advances in large scale nonlinear optimization
Room: 43 (building: 303A)
Chair(s): Simone Rebegoldi, Federica Porta, Elena Morotti, Alessandro Benfenati

• Alternating Projections Methods for Matrix Completion: Regularized and Inexact Projections
  Mattia Silei, Stefania Bellavia, Simone Rebegoldi
• Fractional graph Laplacian for image reconstruction
  Marco Donatelli, Stefano Aleotti, Alessandro Buccini
• A multiplicative components framework for joint correction and segmentation of magnetic resonance images
  Marco Viola, Laura Antonelli, Valentina De Simone
• Convergence analysis of optimization-by-continuation proximal gradient algorithm and some primal-dual extensions
  Ignace Loris

MB-32: Algorithmic Advances in Large Scale Nonconvex Optimization
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Marianna De Santis, Matteo Lapucci

• Don’t be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models
  Leonardo Galli
• A globally convergent gradient method with momentum
  Matteo Lapucci, Giampaolo Liuzzi, Stefano Lucidi
• Stochastic gradient descent with momentum and line-searches
  Davide Pucci, Matteo Lapucci
• A Block Cubic Newton method with Greedy Rule
  Andrea Cristofari

MB-34: Optimization and learning for data science and imaging (Part II)
Stream: Advances in large scale nonlinear optimization
Room: 43 (building: 303A)
Chair(s): Simone Rebegoldi, Federica Porta, Elena Morotti, Alessandro Benfenati

• A Nested Primal–Dual Iterated Tikhonov Method for Regularized Convex Optimization
  Stefano Aleotti, Silvia Bonettini, Marco Donatelli, Marco Prato, Simone Rebegoldi
• Parameter-free FISTA
  Luca Calatroni, Jean-François Aujol, Charles Dossal, Hippolyte Labarrière, Aude Rondepierre
• Solving large-scale nonlinear least-squares with random Gauss-Newton models
  Benedetta Morini, Stefania Bellavia, Greta Malaspina
• Mean square convergence analysis of nonlinear distributed recursive estimation under heavy-tailed noise
  Manojlo Vukovic, Dusan Jakovetic, Dragana Bajovic, Soummya Kar

MC-32: Advances in Complexity of Convex and Nonconvex Problems
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Yurii Nesterov, Geovani Grapiglia

• Minimizing Quasi-Self-Concordant Functions by Gradient Regularization of Newton Method
  Nikita Doikov
• Universal Gradient Methods for Stochastic Convex Optimization
  Anton Rodomanov
• High-Order Reduced-Gradient Methods for Composite Variational Inequalities
  Yurii Nesterov

MC-34: Optimization and learning for data science and imaging (Part III)
Stream: Advances in large scale nonlinear optimization
Room: 43 (building: 303A)
Chair(s): Simone Rebegoldi, Federica Porta, Elena Morotti, Alessandro Benfenati

• Real data EIT reconstruction using virtual X-rays and deep learning
  Siiri Rautio
• Space-Variant Total Variation boosted by learning techniques for subsampled imaging problems
  Davide Evangelista
• On stochastic first order optimization methods for deep learning applications
  Federica Porta, Giorgia Franchini, Valeria Ruggiero, Ilaria Trombini, Luca Zanni
• Accelerating convergent Plug-and-Play methods
  Andrea Sebastiani, Tatiana Bubba, Luca Ratti

MD-32: Algorithms for machine learning and inverse problems: adaptive strategies
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Silvia Villa, Luca Calatroni, Cesare Molinari

• Inertial methods beyond minimizer uniqueness
  Hippolyte Labarrière
• Adaptive restart of conservative dynamics for convex optimization
  Alessandro Scagliotti
• Monitoring the Convergence Speed of PDHG to Find Better Primal and Dual Step Sizes
  Olivier Fercoq
• Stochastic Primal Dual Hybrid Gradient Algorithm with Adaptive Step-Sizes
  Claire Delplancke, Antonin Chambolle, Matthias J. Ehrhardt, Carola-Bibiane Schönlieb, Junqi Tang

MD-34: Preconditioning for Large Scale Nonlinear Optimization
Stream: Advances in large scale nonlinear optimization
Room: 43 (building: 303A)
Chair(s): Panos Parpas

• Loraine – An Interior-Point Solver for Low-Rank Semidefinite Programming
  Soodeh Habibi, Michal Kocvara, Michael Stingl
• Simba: A Scalable Bilevel Preconditioned Gradient Method for Fast Evasion of Flat Areas and Saddle Points
  Nick Tsipinakis, Panos Parpas
• Parallel Neural Network Training via Nonlinearly Preconditioned Trust-Region Method
  Samuel Cruz
• Stochastic Mirror Descent for Convex Optimization with Consensus Constraints
  Panos Parpas

TA-32: Nonsmooth optimization and applications, Part I
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Valentina De Simone, Gerardo Toraldo

• An interior proximal gradient method for nonconvex optimization
  Alberto De Marchi, Andreas Themelis
• Multilevel proximal methods for image restoration
  Guillaume Lauga, Elisa Riccietti, Nelly Pustelnik
• A Scaled Gradient Projection method for the realization of the Balancing Principle in TGV-based image restoration
  Germana Landi, Marco Viola, Fabiana Zama
• A Variational Model for graph p-Laplacian eigenfunctions under p-orthogonality constraints
  Giuseppe Antonio Recupero, Serena Morigi, Alessandro Lanza

TA-34: New Algorithms for Nonlinear Optimization
Stream: Advances in large scale nonlinear optimization
Room: 43 (building: 303A)
Chair(s): Benedetta Morini

• Enhancing the convergence speed of line search methods: Applications in Neural Network training
  José Ángel Martín-Baos, Ricardo Garcia-Rodenas, Luis Rodriguez-Benitez, Maria Luz Lopez
• Sphere covering and approximating tensor norms
  Zhening Li
• First-order Trust-region Methods with Adaptive Sampling
  Sara Shashaani

TB-32: Nonsmooth optimization and applications, Part II
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Valentina De Simone, Gerardo Toraldo

• Bilevel learning optimization and applications
  Serena Crisci
• Nonsmooth optimization in sparse portfolio selection
  Zelda Marino, Stefania Corsaro, Valentina De Simone
• Parallel computing in optimization methods used in estimating risk-neutral densities through option prices
  Antonio Santos, Ana Monteiro

TC-32: Algorithms for machine learning and inverse problems: zeroth-order optimisation
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Silvia Villa, Luca Calatroni, Cesare Molinari

• Zeroth-order implementation of the regularized Newton method with lazy approximated Hessians
  Geovani Grapiglia
• Accelerating Randomized Adaptive Subspace Trust-Region Derivative-Free Algorithms
  Stefan M. Wild, Kwassi Joseph Dzahini, Xiaoqian Liu
• An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization
  Cesare Molinari
• Stochastic derivative-free optimization algorithms using random subspace strategies
  Kwassi Joseph Dzahini, Stefan M. Wild

TD-32: Algorithms for machine learning and inverse problems: optimisation for neural networks
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Silvia Villa, Luca Calatroni, Cesare Molinari

• Differentiating Nonsmooth Solutions to Parametric Monotone Inclusion Problems
  Antonio Silveti-Falls
• Inexact Restoration trust-region algorithm with random models for unconstrained noisy optimization
  Simone Rebegoldi, Benedetta Morini
• Conservation laws for gradient flows
  Sibylle Marcotte
• (Automatic) Iterative Differentiation: some old (& new) results
  Samuel Vaiter

WA-32: Adaptive and Polyak step-size methods
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Dmitry Kamzolov, Martin Takac

• On the Stochastic Polyak Step Size for Machine Learning: Proximal and Momentum Versions
  Fabian Schaipp
• Unveiling the Power of Adaptive Methods Over SGD: A Parameter-Agnostic Perspective
  Xiang Li
• EXTRA-NEWTON: A First Approach to Noise-Adaptive Accelerated Second-Order Methods
  Kimon Antonakopoulos
• AdaBatchGrad: Combining Adaptive Batch Size and Adaptive Step Size
  Petr Ostroukhov

WB-32: Beyond First-Order Optimization Methods
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Dmitry Kamzolov, Martin Takac

• Adaptive Quasi-Newton and Anderson Acceleration Framework with Explicit Global (Accelerated) Convergence Rates
  Damien Scieur
• Accelerated Adaptive Cubic Regularized Quasi-Newton Methods
  Dmitry Kamzolov
• On the behavior of limited-memory quasi-Newton methods for quadratic problems
  Aban Ansari-Önnestam, Anders Forsgren
• Advancing the lower bounds: An accelerated, stochastic, second-order method with optimal adaptation to inexactness
  Artem Agafonov, Dmitry Kamzolov, Alexander Gasnikov, Ali Kavis, Kimon Antonakopoulos, Volkan Cevher, Martin Takac

WC-32: Computer-Assisted Proofs in Optimization
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Eduard Gorbunov

• Constructive approaches to the analysis and construction of optimization algorithms
  Adrien Taylor
• Automated tight Lyapunov analysis for first-order methods
  Manu Upadhyaya, Sebastian Banert, Adrien Taylor, Pontus Giselsson
• Counter-examples in first-order optimization: a constructive approach
  Aymeric Dieuleveut, Adrien Taylor, Baptiste Goujaud
• Provable non-accelerations of the heavy-ball method
  Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut

WD-32: Distributed and Federated Optimization
Stream: Advances in large scale nonlinear optimization
Room: 41 (building: 303A)
Chair(s): Eduard Gorbunov

• TAMUNA: Doubly-Accelerated Distributed Optimization with Local Training, Compression, and Partial Participation
  Laurent Condat, Peter Richtarik
• Machine Learning in Untrusted Distributed Environment
  Nirupam Gupta
• Byzantine Robustness and Partial Participation Can Be Achieved Simultaneously: Just Clip Gradient Differences
  Eduard Gorbunov
• Beyond spectral gap: the role of the topology in decentralized learning
  Hadrien Hendrikx