Program for stream Zeroth and first-order optimization methods

MB-01: Advances in Large-Scale Derivative-Free Optimization
Stream: Zeroth and first-order optimization methods
Room: B100/1001
Chair(s): Francesco Rinaldi, Andrea Cristofari

• Dimensionality reduction techniques for derivative free optimization
  Coralia Cartis
• Solving 10,000-Dimensional Optimization Problems Using Inaccurate Function Values: An Old Algorithm
  Zaikun Zhang
• On the computation of the cosine measure in high dimensions.
  Scholar Sun
• A Novel Stochastic Derivative-Free Trust-Region Algorithm with Adaptive Sampling and Moving Ridge Functions
  Benjamin Rees, Christine Currie, Vuong Phan

MC-01: Strategies to Improve Zeroth-Order Optimization Methods
Stream: Zeroth and first-order optimization methods
Room: B100/1001
Chair(s): Francesco Rinaldi, Andrea Cristofari

• Improving the robustness of zeroth-order optimization solvers
  Stefan M. Wild
• Derivative free optimization with structured random directions
  Silvia Villa, Marco Rando, Cheik Traoré, Cesare Molinari, Lorenzo Rosasco
• Enhancing finite-difference-based derivative-free optimization with machine learning
  Geovani Grapiglia, Timothé Taminiau, Estelle Massart
• A derivative-free algorithm based on resilient positive spanning sets
  Sébastien Kerleau, Clément Royer

MD-01: Derivative-Free Optimization Methods for challenging applications: Handling Nonsmoothness and Constraints
Stream: Zeroth and first-order optimization methods
Room: B100/1001
Chair(s): Francesco Rinaldi, Andrea Cristofari

• Derivative-free Penalty-IPM for nonsmooth constrained optimization
  Andrea Brilli, Youssef Diouane, Sébastien Le Digabel, Giampaolo Liuzzi, Christophe Tribes
• Complexity of a Riemannian Direct-search algorithm
  Bastien Cavarretta, Clément Royer, Florian Yger, Florentin Goyens
• TRFD: A derivative-free trust-region method based on finite differences for composite nonsmooth optimization
  Dânâ Davar, Geovani Grapiglia
• On the Pareto-efficient points of Simple Constrained Multiobjective Problems
  Dimo Brockhoff

MD-10: Interactions between optimization and machine learning
Stream: Zeroth and first-order optimization methods
Room: B100/8011
Chair(s): Cesare Molinari, Silvia Villa

• From learning to optimize to learning optimization algorithms
  Camille Castera, Peter Ochs
• The Surprising Agreement Between Convex Optimization Theory and Learning-Rate Scheduling for Large Model Training
  Fabian Schaipp, Alexander Hägele, Adrien Taylor, Umut Simsekli, Francis Bach
• Greedy learning to optimise with convergence guarantees
  Patrick Fahy, Mohammad Golbabaee, Matthias J. Ehrhardt
• Learning from data via overparameterization
  Cesare Molinari, Silvia Villa, Lorenzo Rosasco, Cristian Vega, Hippolyte Labarrière

TB-01: Zeroth-Order Optimization Methods for Stochastic and Noisy Problems
Stream: Zeroth and first-order optimization methods
Room: B100/1001
Chair(s): Francesco Rinaldi, Andrea Cristofari

• Unifying Trust-region Algorithms with Adaptive Sampling for Nonconvex Stochastic Optimization
  Sara Shashaani, Yunsoo Ha
• Direct Search Methods for Stochastic Zeroth-Order Problems
  Francesco Rinaldi, Andrea Cristofari
• Analysis of derivative-free algorithms on noisy problems
  Alexandre Chotard, Anne Auger
• Derivative-Free Constrained Optimization in Hydraulics: Augmented Lagrangian Method with BOBYQA
  Fabio Fortunato Filho, José Mario Martínez

TC-01: First-Order Methods for Structured Optimization and Sampling
Stream: Zeroth and first-order optimization methods
Room: B100/1001
Chair(s): Cesare Molinari, Silvia Villa

• Constrained sampling with Primal-Dual Langevin Monte Carlo
  Luiz Chamon
• A Fast Extra-Gradient Method with Flexible Anchoring
  Enis Chenchene, Radu Ioan Bot
• Risk-averse guarantees for stochastic min-max problems
  Yassine Laguel, Mert Gürbüzbalaban, Necdet Serhat Aybat, Yasa Syed

WB-01: Advances in stochastic and non-euclidean first order methods
Stream: Zeroth and first-order optimization methods
Room: B100/1001
Chair(s): Cesare Molinari, Silvia Villa

• Non-monotone stochastic line search without overhead for training neural networks
  Andrea Cristofari, Leonardo Galli, Stefano Lucidi
• On the convergence of stochastic Bregman proximal gradient algorithms with biased gradient estimators
  Thomas Guilmeau, Emilie Chouzenoux, Víctor Elvira
• Riemannian gradient descent improves parameter-efficient fine-tuning
  Bingcong Li
• General Tail Bounds for Non-Smooth Stochastic Mirror Descent
  Andrea Paudice, Khaled Eldowa

WC-01: Advances in Multiobjective and Bilevel Optimization without Derivatives
Stream: Zeroth and first-order optimization methods
Room: B100/1001
Chair(s): Francesco Rinaldi, Andrea Cristofari

• A Direct Multisearch Approach (DMS) for Many-Objective Derivative-Free Optimization
  Everton Silva, Ana Luisa Custodio
• Exploring Polynomial Models in the Search Step of Direct Multisearch
  Marta Pozzi, Everton Silva, Ana Luisa Custodio
• Derivative-Free Bilevel Optimization with Inexact Lower-Level Solutions
  Edoardo Cesaroni, Giampaolo Liuzzi, Stefano Lucidi