Program

TE-01: Plenary III - Gabriele Eichfelder EUROPT Fellow
Stream: Plenaries
Room: M:A
Chair(s): Giancarlo Bigi, Pontus Giselsson, Oliver Stein

• Multiobjective optimization, uncertainty, and a bit of set optimization
  Gabriele Eichfelder

TA-01: Plenary II - Amir Beck
Stream: Plenaries
Room: M:A
Chair(s): Giancarlo Bigi

• New results on the multi-dimensional linear discriminant analysis problem
  Amir Beck

WB-01: Plenary I - Gabriel Peyré
Stream: Plenaries
Room: M:A
Chair(s): Pontus Giselsson

• Conservation laws for gradient flows
  Gabriel Peyré

FA-01: Plenary IV - Sebastian Stich
Stream: Plenaries
Room: M:A
Chair(s): Alp Yurtsever

• A Universal Framework for Federated (Convex) Optimization
  Sebastian Stich

WC-05: Optimization for learning I
Stream: Optimization for learning
Room: M:N
Chair(s): Manu Upadhyaya

• Incorporating History and Deviations in Forward-Backward Splitting
  Pontus Giselsson
• Optimal Acceleration for Minimax and Fixed-Point Problems is Not Unique
  TaeHo Yoon, Jaeyeon Kim, Jaewook Suh, Ernest Ryu
• Accelerated Algorithms For Nonlinear Matrix Decomposition With The Relu Function
  Giovanni Seraghiti, Arnaud Vandaele, Margherita Porcelli, Nicolas Gillis

WA-01: Opening session
Stream: Opening session
Room: M:A
Chair(s): Pontus Giselsson

WD-05: Optimization for learning II
Stream: Optimization for learning
Room: M:N
Chair(s): Manu Upadhyaya

• Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
  Hanmin Li, Avetik Karagulyan, Peter Richtarik
• Optimization flows landing on the Stiefel manifold: continuous-time flows, deterministic and stochastic algorithms
  Bin Gao, P.-A. Absil
• Is maze-solving parallelizable?
  Romain Cosson

WE-02: Recent advances in computer-aided analyses of optimization algorithms I
Stream: Conic optimization: theory, algorithms and applications
Room: M:O
Chair(s): Adrien Taylor, Manu Upadhyaya

• Last-Iterate Convergence of Extragradient-based Methods
  Eduard Gorbunov, Adrien Taylor, Samuel Horvath, Nicolas Loizou, Gauthier Gidel
• Automated tight Lyapunov analysis for first-order methods
  Manu Upadhyaya, Sebastian Banert, Adrien Taylor, Pontus Giselsson
• Second-order interpolation conditions for univariate functions, towards a tight analysis of second-order optimization methods
  Anne Rubbens, Nizar Bousselmi, Julien Hendrickx, François Glineur
• Analysis of Second-Order Methods via non-convex Performance Estimation
  Nizar Bousselmi, Anne Rubbens, Julien Hendrickx, François Glineur

WD-02: Conic and polynomial optimization
Stream: Conic optimization: theory, algorithms and applications
Room: M:O
Chair(s): Immanuel Bomze

• Uncertain standard quadratic optimization under distributional assumptions: a chance-constrained epigraphic approach
  Immanuel Bomze, Daniel de Vicente
• On Tractable Convex Relaxations of Standard Quadratic Optimization Problems under Sparsity Constraints
  Bo Peng, Immanuel Bomze, Yuzhou Qiu, E. Alper Yildirim
• New results for sparse conic reformulations
  Markus Gabl

TD-02: Recent advances in computer-aided analyses of optimization algorithms III
Stream: Conic optimization: theory, algorithms and applications
Room: M:O
Chair(s): Adrien Taylor, Manu Upadhyaya

• Provable non-accelerations of the heavy-ball method
  Aymeric Dieuleveut, Adrien Taylor, Baptiste Goujaud
• Provable non-accelerations of the heavy-ball method
  Baptiste Goujaud, Adrien Taylor, Aymeric Dieuleveut
• Exact convergence rates of the last iterate in subgradient methods
  François Glineur, Moslem Zamani
• Algorithms with learned deviations
  Sebastian Banert

WE-06: Higher-order Methods in Mathematical Programming I
Stream: Challenges in nonlinear programming
Room: M:H
Chair(s): Mathias Staudigl

• Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions
  Nikita Doikov
• Barrier Algorithms for Constrained Non-Convex Optimization
  Pavel Dvurechensky, Mathias Staudigl
• Accelerated cubic regularized quasi-newton methods
  Dmitry Kamzolov
• Relaxation Approaches for Nonlinear Sparse Optimization Problems
  Steffensen Sonja

WF-06: Stochastic Gradient Methods: Bridging Theory and Practice
Stream: Challenges in nonlinear programming
Room: M:H
Chair(s): Simon Weissmann

• Stochastic Optimization under Hidden Convexity
  Ilyas Fatkhullin, Niao He, Yifan Hu
• On Almost Sure Convergence Rates for Stochastic Gradient Methods
  Sara Klein
• Optimal sampling for stochastic and natural gradient descent
  Robert Gruhlke, Philipp Trunschke, Anthony Nouy
• Stochastic gradient methods and tame geometry
  Johannes Aspman, Jiri Nemecek, Vyacheslav Kungurtsev, Fabio V. Difonzo, Jakub Marecek

WF-02: Recent advances in computer-aided analyses of optimization algorithms II
Stream: Conic optimization: theory, algorithms and applications
Room: M:O
Chair(s): Adrien Taylor, Manu Upadhyaya

• Exact worst-case convergence rates of gradient descent: a complete analysis for all constant stepsizes over nonconvex and convex functions
  Teodor Rotaru, François Glineur, Panagiotis Patrinos
• A Linear-Quadratic Program for Estimating Performance of Convex Optimization Algorithm
  Ashkan Panahi
• On the convergence rate of the difference-of-convex algorithm (DCA)
  Hadi Abbaszadehpeivasti
• Non-expansiveness for frugal resolvent splitting methods, using PEP
  Anton Åkerman, Emanuele Naldi, Enis Chenchene, Sebastian Banert, Pontus Giselsson

FB-04: Large-scale optimization II
Stream: Large-scale optimization
Room: M:M
Chair(s): Anton Åkerman

• An interior proximal gradient method for nonconvex optimization
  Alberto De Marchi, Andreas Themelis
• Krasnoselskii-Mann Iterations: Inertia, Perturbations and Approximation
  Daniel Cortild, Juan Peypouquet
• A Fast Optimistic Method for Monotone Variational Inequalities
  Michael Sedlmayer, Dang-Khoa Nguyen, Radu Ioan Bot

FD-06: Difference and decomposition methods
Stream: Methods for non-/monotone inclusions and their applications
Room: M:H
Chair(s): Dânâ Davar

• Douglas-Rachford DC methods for generalized DC programming
  AVINASH DIXIT
• Revisiting Frank-Wolfe for Nonconvex Problems
  Hoomaan Maskan, Suvrit Sra, Alp Yurtsever
• Penalty Decomposition methods for convex and nonconvex market equilibrium models
  Giulio Scarponi, Marco Sciandrone
• A derivative-free trust-region method based on finite differences for composite nonsmooth optimization
  Dânâ Davar, Geovani Grapiglia

TD-05: Nonsmooth optimization algorithms
Stream: Nonsmooth and nonconvex optimization algorithms
Room: M:N
Chair(s): Susan Ghaderi

• A feasible directions method for nonconvex optimization over linear constraints with a nonsmooth concave regularizer
  Nadav Hallak, Amir Beck
• Spectral and nuclear norms of order three tensors: Complexity and computation
  Zhening Li
• High-order Moreau envelope in nonsmooth convex setting: L-smoothness and inexact gradient method
  Alireza Kabgani, Masoud Ahookhosh
• Scaled gradient methods under convexity and local smoothness
  Susan Ghaderi, Yves Moreau, Masoud Ahookhosh

FD-02: Deterministic and stochastic optimization beyond Euclidean geometry
Stream: Advances in first-order optimization
Room: M:O
Chair(s): Adrien Taylor, Hadrien Hendrikx

• Horospherically Convex Optimization on Hadamard Manifolds
  Christopher Criscitiello, Jungbin Kim
• Implicit Regularisation of Mirror Flow on Separable Classification Problems
  Radu-Alexandru Dragomir
• ACCELERATED BREGMAN DIVERGENCE OPTIMIZATION WITH SMART: AN INFORMATION GEOMETRIC POINT OF VIEW
  Stefania Petra
• Investigating Variance Definitions for Stochastic Mirror Descent with Relative Smoothness
  Hadrien Hendrikx

WC-02: Conic and Semidefinite Optimization
Stream: Conic optimization: theory, algorithms and applications
Room: M:O
Chair(s): Miguel Anjos

• Learning to Relax Nonconvex Quadratically Constrained Quadratic Programs
  Burak Kocuk, Buket Özen
• Beyond Traditional PCA: The Two-Step-SDP Algorithm for Data Analysis
  Eloisa Macedo
• Semidefinite liftings for the complex cut polytope
  Miguel Anjos, Lennart Sinjorgo, Renata Sotirov

TB-05: Optimization for learning III
Stream: Optimization for learning
Room: M:N
Chair(s): Max Nilsson

• MAST: Model-Agnostic Sparsified Training
  Egor Shulgin, Peter Richtarik
• Online Learning and Information Exponents: The Importance of Batch size & Time/Complexity Tradeoffs
  Stephan Ludovic
• Compressed and distributed least-squares regression: convergence rates with applications to Federated Learning
  Constantin Philippenko, Aymeric Dieuleveut

TB-03: In memory of Georg Still - part 1
Stream: In memory of Georg Still
Room: M:J
Chair(s): Oliver Stein

• On the weakest constraint qualification for sharp local minimizers
  Oliver Stein, Maximilian Volk
• Copositive and semi-infinite optimization
  Mirjam Duer
• A reflection on the work of Georg Still on semi-infinite linear optimization
  Etienne De Klerk