Program for stream Optimization for machine learning

MB-05: Optimization and machine learning I
Stream: Optimization for machine learning
Room: B100/4013
Chair(s): Laurent Condat, Avetik Karagulyan

• Laplacian Regularization in Semi-Supervised Learning with Functional Data
  Zhengang Zhong
• When to Forget? Complexity Trade-offs in Machine Unlearning
  Martin Van Waerebeke, Marco Lorenzi, Gioanni Neglia, Kevin Scaman
• Searching for optimal per-coordinate stepsizes with multidimensional backtracking
  Frederik Kunstner, Victor Sanches Portella, Nick Harvey, Mark Schmidt
• Automatic recommendation of optimization methods through their worst-case complexity
  Sofiane Tanji, François Glineur

MC-05: Optimization and machine learning II
Stream: Optimization for machine learning
Room: B100/4013
Chair(s): Laurent Condat

• Stabilized Proximal-Point Methods for Federated Optimization
  Xiaowen Jiang, Anton Rodomanov, Sebastian Stich
• A primal-dual algorithm for variational image reconstruction with learned convex regularizers
  Hok Shing Wong
• Entropic Mirror Descent for Linear Systems: Polyak’s Stepsize and Implicit Bias
  Alexander Posch, Yura Malitsky

MD-05: Relaxed Smoothness and Convexity Assumptions in Optimization for Machine Learning
Stream: Optimization for machine learning
Room: B100/4013
Chair(s): Eduard Gorbunov

• Loss Landscape Characterization of Neural Networks without Over-Parametrization
  Rustem Islamov
• Methods for Convex (L0,L1)-Smooth Optimization: Clipping, Acceleration, and Adaptivity
  Eduard Gorbunov
• Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods
  Anton Rodomanov, Daniil Vankov, Angelia Nedich, Lalitha Sankar, Sebastian Stich
• A Third-Order Perspective on Newton’s Method and its Application in Federated Learning
  Slavomír Hanzely

TB-05: Randomized Optimization algorithms I
Stream: Optimization for machine learning
Room: B100/4013
Chair(s): Laurent Condat

• Scalable Second-Order Optimization Algorithms for Minimizing Low-Rank Functions
  Edward Tansley, Coralia Cartis, Zhen Shao
• Distributed Optimization with Communication Compression
  Yuan Gao, Sebastian Stich
• Stochastic Gradient Descent without Variance Assumption: A Tight Lyapunov Analysis
  Lucas Ketels, Daniel Cortild, Guillaume Garrigos, Juan Peypouquet
• Communication-Efficient Algorithms for Federated Learning and Weakly Coupled Games
  Sebastian Stich, Ali Zindari, Parham Yazdkhasti, Anton Rodomanov, Tatjana Chavdarova

TC-05: Randomized Optimization algorithms II
Stream: Optimization for machine learning
Room: B100/4013
Chair(s): Laurent Condat

• Derivative-free stochastic bilevel optimization for inverse problems
  Mathias Staudigl, Simon Weissmann, Tristan van Leeuwen
• Proximal splitting algorithms in nonlinear spaces
  Russell Luke
• SPAM: Stochastic Proximal Point Method with Momentum Variance Reduction for Non-convex Cross-Device Federated Learning
  Avetik Karagulyan
• A Stochastic Newton-type Method for Non-smooth Optimization
  Titus Pinta

WB-04: Optimization and learning for estimation problems
Stream: Optimization for machine learning
Room: B100/5013
Chair(s): Laurent Condat

• Multilevel Plug-and-Play Image Restoration
  Nils Laurent, Julian Tachella, Elisa Riccietti, Nelly Pustelnik
• Anomaly Detection Using the Cloud of Spheres Classification Method
  Paula Amaral, Tiago Dias
• Learning Proximal Neural Networks at Equilibrium Without Jacobian
  Leo Davy, Nelly Pustelnik, Luis Briceño-Arias
• Resource-Constrained Plug-and-Play Imaging: a block proximal heavy ball approach
  Andrea Sebastiani, Federica Porta, Simone Rebegoldi

WB-05: Recent advances in min-max optimization
Stream: Optimization for machine learning
Room: B100/4013
Chair(s): Ali Kavis, Aryan Mokhtari

• Steering Towards Success: Efficient Methods for Nonconvex-Nonconcave Minimax Problems
  Pontus Giselsson, Anton Åkerman, Max Nilsson, Manu Upadhyaya, Sebastian Banert
• A Universally Optimal Primal-Dual Method for Minimizing Heterogeneous Compositions
  Benjamin Grimmer
• Parameter-free second-order methods for min-max optimization
  Ali Kavis, Ruichen Jiang, Qiujiang Jin, Sujay Sanghavi, Aryan Mokhtari

WC-04: Large Scale Optimization for Statistical Learning
Stream: Optimization for machine learning
Room: B100/5013
Chair(s): Selin Ahipasaoglu

• Spatial branch-and-bound methods for solving the k-Hyperplane clustering
  Stefano Coniglio, Montree Jaidee
• Solving the Optimal Experiment Design with Mixed-Integer Convex Methods
  Deborah Hendrych, Mathieu Besançon, Sebastian Pokutta
• A column generation approach to exact experimental design
  Selin Ahipasaoglu, Stefano Cipolla, Jacek Gondzio

WC-05: Recent Advances in Stochastic Optimization
Stream: Optimization for machine learning
Room: B100/4013
Chair(s): Chuan He

• Almost sure convergence rates for stochastic gradient methods
  Simon Weissmann
• A Hessian-Aware Stochastic Differential Equation for Modelling SGD
  Xiang Li
• Complexity guarantees for risk-neutral generalized Nash equilibrium problems
  Meggie Marschner, Mathias Staudigl
• Stochastic first-order methods can leverage arbitrarily higher-order smoothness for acceleration
  Chuan He

WC-08: Advances in non-convex optimization
Stream: Optimization for machine learning
Room: B100/7007
Chair(s): Radu-Alexandru Dragomir

• Benign landscapes for synchronization on spheres via normalized Laplacian matrices
  Andrew McRae
• Diagonal linear networks and the regularization path of the LASSO
  Raphael Berthier
• Long-time convergence of a consensus-based optimization method
  Victor Priser, Pascal Bianchi, Radu-Alexandru Dragomir
• Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data
  Nikola Konstantinov