Program for stream Advances in mathematical optimization for machine learning

WC-02: Advances in mathematical optimization for machine learning and data analysis - Part I
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s): Le Thi Khanh Hien

• An adaptive subsampled Hessian-free optimization method for statistical learning.
  Jeremy RIEUSSEC, Fabian Bastin, Jean Laprés-Chartrand, Loïc Shi-Garrier
• An Inertial Newton Algorithm for Deep Learning
  Camille Castera, Jerome Bolte, Cédric Févotte, Edouard Pauwels
• An Inertial Block Majorization Minimization Framework for Nonsmooth Nonconvex Optimization
  Le Thi Khanh Hien, Duy Nhat Phan, Nicolas Gillis

WD-02: Advances in mathematical optimization for machine learning and data analysis - Part II
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s):

• A Bregman Method for Structure Learning on Sparse Directed Acyclic Graphs
  Manon Romain
• An adaptive, accelerated algorithm for stochastic constrained convex optimization
  Ali Kavis, Kfir Levy, Francis Bach, Volkan Cevher
• Recent Advanced in the Theory of (Adaptive) Stochastic Gradient Methods
  Vivak Patel

WF-02: Beyond First-order Optimization Methods for Machine Learning - Part I
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s): Fred Roosta, Albert Berahas

• Sequential Quadratic Optimization for Nonlinear Equality Constrained Stochastic Optimization
  Albert Berahas, Frank E. Curtis
• Stochastic Polyak Step-size for SGD: An Adaptive Learning Rate for Fast Convergence
  Nicolas Loizou
• Systematic Second-order Methods for Training, Designing, and Deploying Neural Networks
  Amir Gholami
• Distributed Learning of Deep Neural Networks using Independent Subnet Training
  Anastasios Kyrillidis

TA-02: Nonlinear Composite and Constrained Optimization - Part I
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s):

• Proximal alternating minimization for solving discrete Mumford-Shah and Amborsio-Tortorelli models
  Hoang Trieu Vy LE, Marion Foare, Nelly Pustelnik
• Random extrapolation for primal-dual coordinate descent
  Ahmet Alacaoglu, Olivier Fercoq, Volkan Cevher
• Primal-Dual Proximal Splitting Algorithms for Large-Scale Convex Optimization
  Laurent Condat, Adil Salim, Peter Richtarik
• On a Primal-Dual Newton Proximal Method for Convex Quadratic Programs
  Alberto De Marchi

TB-02: Nonlinear Composite and Constrained Optimization - Part II
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s):

• A primal dual method for optimization with nonlinear constraints
  Mehmet Fatih Sahin
• Safe Screening for the Generalized Conditional Gradient Method
  Yifan Sun
• An Optimal Algorithm for Strongly Convex Minimization under Affine Constraints
  Adil Salim, Laurent Condat, Dmitry Kovalev, Peter Richtarik
• Larger stepsizes for some primal-dual algorithms
  Ming Yan, Zhi Li

TD-02: Advances in Douglas-Rachford method - Part I
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s):

• Split-Douglas-Rachford for composite monotone inclusions and Split-ADMM
  Luis Briceño-Arias, Fernando Roldán
• Anderson Accelerated Douglas-Rachford Splitting
  Anqi Fu, Junzi Zhang, Stephen Boyd
• Douglas-Rachford splitting and ADMM for nonconvex optimization: Accelerated and Newton-type algorithms
  Lorenzo Stella, Andreas Themelis, Panagiotis Patrinos

TE-02: Beyond First-order Optimization Methods for Machine Learning - Part II
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s): Fred Roosta, Albert Berahas

• Full-low evaluation type methods for derivative-free optimization
  Luis Nunes Vicente, Albert Berahas, Oumaima Sohab
• Invexification of Non-Linear Least-Squares Problems
  Fred Roosta
• Inexact Restoration with Subsampled Trust-region methods for finite-sum minimization
  Stefania Bellavia, Natasa Krejic, Benedetta Morini
• Retrospective Approximation for Stochastic Optimization
  Raghu Bollapragada
• Global optimization using random embeddings
  Estelle Massart, Coralia Cartis, Adilet Otemissov

FA-02: Beyond First-order Optimization Methods for Machine Learning - Part III
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s): Fred Roosta, Albert Berahas

• Large-scale derivative-free optimization using subspace methods
  Lindon Roberts, Coralia Cartis
• Efficient Newton Methods for Robust Stochastic Nonconvex Optimization
  Thomas O'Leary-Roseberry, Nick Alger, Omar Ghattas
• A stochastic second order-type extra-step scheme for nonsmooth nonconvex optimization
  Andre Milzarek, Minghan Yang, Zaiwen Wen, Tong Zhang
• Doubly Adaptive Scaled Algorithm for Machine Learning Using Second-Order Information
  Martin Takac, Majid Jahani, Sergey Rusakov, Zheng Shi, Peter Richtarik, Michael Mahoney

FB-02: Advances in Douglas-Rachford method - Part II
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s):

• Shadow Douglas-Rachford splitting
  Matthew Tam
• The Cyclic Douglas-Rachford Algorithm with r-sets-Douglas-Rachford Operators
  Aviv Gibali, Francisco Javier Aragón Artacho, Yair Censor
• Forward-partial inverse-half-forward splitting algorithm for solving monotone inclusions with applications
  Yuchao Tang
• Multivariate Monotone Inclusions in Saddle Form
  Patrick Combettes, Minh Bui

FD-02: Advances in mathematical optimization for machine learning and data analysis - Part III
Stream: Advances in mathematical optimization for machine learning
Room: Turing
Chair(s):

• Mixed integer optimization in ARMA models
  Leonardo Di Gangi
• Model of Optimal Centroids Approach For Multivariate Data Classification
  Pham Van Nha, Le Cam Binh
• IGLOO: A stochastic global optimization algorithm to predict the structure of biomolecules adsorbed on metal surfaces
  Juan CORTES, Nathalie TARRAT, Christian Schoen