Skip to yearly menu bar Skip to main content

Workshop Fri, Dec 11, 2026 • 8:00 AM – 5:00 PM AEDT Hall 1

OPT 2026: Optimization for Machine Learning

Frederik Kunstner ⋅ Michael Crawshaw ⋅ Courtney Paquette ⋅ Fred Roosta ⋅ Sebastian Stich ⋅ Chulhee Yun

[ OpenReview]

Abstract

This year marks the 18th edition of the long-running NeurIPS Workshop on Optimization for Machine Learning (OPT). OPT 2025 was a tremendous success, attracting over 160 paper submissions, a 30% increase over the previous year, and featuring 5 plenary speakers, 6 contributed talks, and 2 highly attended poster sessions with more than 400 participants. Widely regarded as one of the premier venues at the intersection of optimization and machine learning, the workshop has become a key forum for presenting cutting-edge research and fostering collaboration across the community. In particular, it serves as an important venue for early-career researchers, many of whom view OPT as the leading workshop for frontier research in optimization and machine learning. Over its 18-year history, OPT has played a central role in bringing together researchers from diverse backgrounds, catalyzing collaborations that have gone on to produce influential research at top-tier venues. Its impact on shaping the optimization and machine learning communities cannot be overstated.

Chat is not available.

Schedule

Time zone: Conference local time zone

8:45 AM

Introduction

Frederik Kunstner

9:00 AM

Invited talk 1

Mateo Díaz

9:30 AM

Contributed Talk 1&2

10:00 AM

Poster session 1 -- Odd ID

11:00 AM

Invited talk 2

Lénaïc Chizat

11:30 AM

Contributed Talk 3&4

12:00 PM

Lunch

2:00 PM

Invited talk 3

Madeleine Udell

2:30 PM

Contributed Talk 5&6

3:00 PM

Poster session 2 -- Even ID

4:00 PM

Invited talk 4

Aaron Defazio

4:30 PM

Invited talk 5

Jeremy Cohen

4:59 PM

Closing Remarks

Sebastian Stich

Muown Implicitly Performs Angular Step-size Decay

Florian Hübler ⋅ Kai Lion ⋅ Antonio Orvieto ⋅ Niao He

Parallelising Matrix-Products in Isotropic Multilayer Perceptrons

George Bird

From Curvature to Scaling Laws: Atomic-Norm Regularization Paths in Quadratic Feature Learning

Hee-Sung Kim ⋅ Sungyoon Lee

Adaptive Quantile Clipping under Heavy-Tailed Noise and Differential Privacy

Ayoub E Gourari ⋅ Anastasia Koloskova

Surrogate Loss Gradient Descent in Variational Inequalities with Linear Approximation

Ryan D'Orazio ⋅ Sadhana Anand ⋅ Ioannis Mitliagkas ⋅ Gauthier Gidel

Adaptive Hyper-parameter Transfer for Adaptive Step Sizes

Davide Pucci ⋅ Leonardo Galli ⋅ Matteo Lapucci ⋅ Holger Rauhut

Principled Top-$k$ Selection for Language Models with Hybrid Gradients

Xuchen Gong ⋅ Junfei Sun ⋅ Tian Li

A Tight Lower Bound for Smooth Nonconvex Stochastic Optimization with Bounded Gradient Noise

Jikai Jin

Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization

Hanyang Li ⋅ Shao Tang ⋅ Daniel T Braithwaite ⋅ Gregory Dexter ⋅ Leonardo Neves ⋅ Aman Gupta ⋅ Hiroto Udagawa ⋅ Abhishek Shivanna ⋅ Daniel Silva ⋅ Rohan Ramanath

When Does Muon Actually Win? A Paired Data-, Time-, and Tuning-Budget Benchmark

Mushir Akhtar ⋅ Hazem N Nounou ⋅ Majdi Mansouri ⋅ Mohamed N Nounou

Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD

Junghoon Seo

An Explicit Basin for Nesterov Acceleration under Local PL near a Manifold of Minimizers

Robert Förster ⋅ Max Obreiter ⋅ Tobias Steinbrecher

When Best-of-Both-Worlds Is Impossible: Terminal-Ratio Bandits

Tianyi Gao

Mirror Descent at the Edge of Stability

Vincent Wang ⋅ Vikas Garg

Adam or Gauss-Newton? A Comparative Study In Terms of Basis Alignment and SGD Noise

Bingbin Liu ⋅ Rachit Bansal ⋅ Depen Morwani ⋅ Nikhil Vyas ⋅ David Alvarez-Melis ⋅ Sham Kakade

Optimizer or Precision? Understanding Optimizer–Precision Interactions in PINNs

Michael Tarekegn ⋅ Chloe Wu ⋅ Trisha Sharma ⋅ Shivank Garg

Gradient Conflict in Multimodal Pretraining

Sreya R Chowdhury ⋅ Sofiia Kononovych ⋅ Ge Shan ⋅ Sahar Rajabi ⋅ Sirisha Rambhatla

Small Batch Noise Restores Simplicity Bias of Muon

Tom Jacobs ⋅ Rebekka Burkholz

Line Search in Federated Learning: Local Descent, Global Extrapolation

Geetika . ⋅ Bapi Chatterjee

Subspace Levenberg–Marquardt Algorithms in Training Neural Networks

Minh Duc Hoang

General convergence rates of stochastic heavy ball with Polyak step size and Armijo line search

Jiawei Zhang ⋅ Yuantao Gu

What is the role of Learning Rate in a Mixture-of-Experts ResNet

Mateusz Pyla ⋅ Igor T Podolak ⋅ Stanislaw Jastrzebski

The Renaissance of Line Search for Deep Learning?

Chongwei Chen ⋅ Yuxiang Wan ⋅ Wenjie Zhang ⋅ Sinian Zhang ⋅ Lingjie Su ⋅ Ju Sun

Global Optimization via Softmin Energy Minimization

Samuele Saviozzi ⋅ Andrea Agazzi ⋅ Marco Romito ⋅ Vittorio Carlei

Anisotropic Trust Region Warping for Prior-Data Fitted Networks in Bayesian Optimisation

Samuel Younger ⋅ Tinkle Chugh ⋅ George De Ath

Zero-order Parameter-free Optimization for LMO-based Methods: Novel Approach for Efficient Fine-tuning

Dmitriy Bystrov ⋅ Daniil Medyakov ⋅ Dmitry Bylinkin ⋅ Aleksandr Beznosikov

Adaptive Bregman Alternating Projections for Feasible Gromov--Wasserstein Learning

Aoran Zhang ⋅ Cesar Uribe

Compositional Generation with Pareto-aware Joint Energy Based Models

Ben Ma ⋅ Yatao Bian

Optimizer Memory Schedules for Outscaling the Overtraining Axis

Katie Everett ⋅ Shikai Qiu

Stochastic Nonconvex Bilevel Optimization: Improved Rates Without Rare-Visit Assumption

Daniel Cortild ⋅ Mathias Staudigl ⋅ Juan Peypouquet ⋅ Coralia Cartis

Accelerated Predictive Coding Networks via Direct Kolen-–Pollack Feedback Alignment

Davide Casnici ⋅ Martin Lefebvre ⋅ Justin Dauwels ⋅ Charlotte Frenkel

Low Rank Adaptive Friction for Memory-Efficient LLM Pretraining

Rajit Rajpal ⋅ Benedict Leimkuhler

One Size Does Not Fit All: Curvature-Aware Adaptive Perturbation for SAM

Alessia Rossi ⋅ Felipe Campelo ⋅ Gabriel Leivas Oliveira

Attention Geometry Helps Early: Mirror-Descent Updates for Transformer Query and Key Matrices

Kumar Kshitij Patel ⋅ Naren Manoj

Sign Descent Sees the Internal Basis: Opposite Learning Orders in Deep Matrix Factorization

Arman Lotfalikhani ⋅ Connall Garrod ⋅ Christos Thrampoulidis

SABLE-X: A Sparsity-Preserving GPU System for Batched Differentiable Nonlinear Solves in End-to-End Learning

Suho Park ⋅ Keunju Song ⋅ Hongseok Kim

From Geometry to Generalization: Why Row Normalization Can Beat Adam and Muon

Jihwan Kim ⋅ Dogyoon Song ⋅ Chulhee Yun

Second-Order Optimization with Asynchronous Curvature

El Mahdi Chayti ⋅ Martin Jaggi

LionMuon: Alternating Spectral and Sign Descent for Efficient Training

Arman Bolatov ⋅ Artem Riabinin ⋅ Nikita M Kornilov ⋅ Andrey Veprikov ⋅ Samuel Horváth ⋅ Martin Takac ⋅ Aleksandr Beznosikov

ProTuon: Progressive Tucker--Muon with Function-Preserving Rank Growth

Rustam Kabirov ⋅ Alexander Miasnikov ⋅ Vladimir Aletov ⋅ Nail Bashirov ⋅ Gleb Molodtsov ⋅ Aleksandr Shestakov ⋅ Aleksandr Beznosikov

Spectral Weight Decay: Inducing Low-Rank Structure in Neural Network Weights

Dmitrii Andriianov ⋅ Andrey Veprikov ⋅ Aleksandr Beznosikov

Stronger Lower Bounds for (Non-)Anytime Acceleration of Gradient Descent

Minchan Jung ⋅ Hanseul Cho ⋅ Chulhee Yun

ZEMA: confidence-calibrated signed descent with only one state.

Ali Dadsetan ⋅ Domenic Rosati ⋅ Frank Rudzicz

Demystifying Pipeline Parallelism: First Theory for PipeDream

Ivan Ilin ⋅ Peter Richtarik

Multiple Descent for Random-Design Ridge Regression under Optimal Regularization and Independent Noise

Maxim Bochkov ⋅ Fedor Noskov

Minimal-norm univariate two-layer ReLU classification: Exact solutions and global optimality with skip connections

Karolina Drabik ⋅ Ben Lewis ⋅ Antoni Puch ⋅ Etienne Boursier ⋅ Piotr Hofman ⋅ Matthias Englert ⋅ Ranko Lazic

Revisiting Gradient-Normalized Linear Scalarization for Multi-Task Learning

Wenzhi HAN ⋅ Zhekai Liu ⋅ Junchi YANG

Discount-Guided Policy Gradient for Average-Reward Optimization

Ian Hsieh ⋅ Po-An Wang

Protected Group-Relative Policy Gradients: Convergence with Informative Completion Times

Yury Demidovich ⋅ Kirill Acharya ⋅ Peter Richtarik

Stochastic Line Search under Nonuniform Smoothness beyond Interpolation

Jun-Hyun Kim ⋅ Mark Schmidt

Beyond Rate Optimality: How Polyak’s Momentum Shapes Non-Convex Optimization

Donghwa Kim ⋅ Chulhee Yun

PDE-State Conditioning for Learned Optimization Using Physics-Informed Neural Networks

Farzana Yasmin ⋅ Ricardo Vilalta

AF-Muon: An AdamW-Free Muon Optimizer for Tied-Embedding Models

Arash Lagzian ⋅ Paniz Halvachi ⋅ Junming Zhang ⋅ Zhouhan Lin ⋅ Dianbo Liu

On the Finite-Time Convergence for Intrinsic Decentralized Riemannian Optimization

Duc Toan Nguyen ⋅ Cesar Uribe

Multilinear Approximate Carathéodory Theorem for Sparse Game Optimization

Martin Balko

Diagnosing Recurrent Computation Reuse under Multitask Optimization

Tomoyuki Unno ⋅ Ichigaku Takigawa

OOCO: Objective-Oriented Content Optimization on Discrete Symbolic Manifolds

Amirfarrokh Iranitalab ⋅ Emily Chen ⋅ Yao Zhang ⋅ Neil Kumar ⋅ Swapnil Shinde ⋅ Pranab Mohanty

Curvature-Aware Clipping: Mitigating Bias in DPSGD via Approximate Second-Order Information

Xincheng Xu ⋅ Thilina Ranbaduge ⋅ Thierry Rakotoarivelo ⋅ David Smith

Muon Under Covariate Shift: Spectral Learning and Temporal Stability

Dmitrii Feoktistov ⋅ Andrey Veprikov ⋅ Aleksandr Beznosikov

A Defense of the Quadratic Model

Alexandru Meterez ⋅ Pranav Nair ⋅ Depen Morwani ⋅ Cengiz Pehlevan ⋅ Sham Kakade ⋅ Alex Damian

Exact Branch-and-Bound for Subgraph-Count Splits in Second-Order Tree Boosting

Kentaro Nishioka ⋅ Ichigaku Takigawa

Is Beating Adam Enough? Operator Conditioning and the Accuracy of Squared-Residual PDE Solvers

Aviad Lengo ⋅ Ali Keshavarzi

Stochastic Compositional Optimization via Hybrid Momentum Frank--Wolfe

El Mahdi Chayti

How Does Muon Work in Private Deep Learning? Scalable Differentially Private Training via Orthogonalization

Alexander Gaponov ⋅ Grigory Malinovsky ⋅ Egor Shulgin ⋅ Peter Richtarik

Self-Supervised Combinatorial Optimization with Constraints via Frank–Wolfe

Akbar Rafiey ⋅ Yifei Xu ⋅ Nikolaos Karalias

Gradient Clipping on Separable Data: Asymptotic Alignment and Persistent Bias

Mansouri ⋅ Nima Mollaei ⋅ Yongtao Wu

Optimal Algorithms for Nonsmooth Nonconvex Stochastic Optimization with Constraints

Gon Buzaglo ⋅ Guy Kornowski

Recent Training is Protected by Adam's Second Moment

Shrey Biswas

Optimizers Select Algorithms: Update Geometry Controls Memory Strategy in Associative Recall

Matevz Matjasec ⋅ Antonio Orvieto

Machine Unlearning with a Destination: Tracking a Minimizer Path to the Retain-Only Objective

Chaewon Moon ⋅ Yeseul Cho ⋅ Chulhee Yun

Online Submodular Minimization with Switching Costs

Yuki Nakagawa ⋅ Shinji Ito

Optimizer Update Geometry: How Parameter Groups Shape Curvature Exposure

Georg Tirpitz ⋅ Antonio Orvieto

Monarch–Muon: Structure-Aware Muon for Fast and Memory-Efficient Pretraining

Ruslan Kabirov ⋅ Alexander Miasnikov ⋅ Dmitrii Vlashchuk ⋅ Gleb Molodtsov ⋅ Vladimir Aletov ⋅ Nail Bashirov ⋅ Aleksandr Shestakov ⋅ Daniil Tikhonov ⋅ Maxim Krutikov ⋅ Aleksandr Beznosikov

From Inner Randomness to Outer Stability

Nishant Sharma ⋅ Ganesh Talluri ⋅ Hiroki Naganuma

Linear Bandits under Exact Cyclic Sliding-Window Constraints

Seyed Mohammad Hadi Hosseini ⋅ Sattar Vakili

Residual Cancellation and Sharp Data-Selection Bounds for Least Squares

Roshan Saxena

Increasing-Batch AdGD under Glocal Smoothness

Jun-Hyun Kim ⋅ Param Mody ⋅ Curtis Fox ⋅ Mark Schmidt

Can Acceleration in Gradient-Norm Minimization Be Anytime? Sharp Last-Iterate Limits in Smooth Convex Optimization

Pierre Vernimmen ⋅ François Glineur

BOND: License to Train with Black-Box Functions

Andrew Clark ⋅ Osmaan Rasouli ⋅ Jack Moursounidis ⋅ William Gan ⋅ Cooper Doyle

DyKAF: Dynamical Kronecker Approximation of the Fisher Information Matrix for Gradient Preconditioning

Nikolay Yudin ⋅ Ekaterina Grishina ⋅ Andrey Veprikov ⋅ Aleksandr Beznosikov ⋅ Maxim Rakhuba

Toward a First-Principles Update Geometry for the Language-Model Head

Aditya Somasundaram ⋅ Charles Guille-Escuret ⋅ Alexander Moreno ⋅ Zhengzhong Liu ⋅ Eric Xing

Critical-Point Geometry and Saddle Escape in Overparameterized Neural Optimization

Ranjan Veerabhadraswamy ⋅ Ajith J E

Federated Learning via Spectral Methods with Compressed Communication and Local Steps

Dmitriy Bystrov ⋅ Daniil Medyakov ⋅ Dmitry Bylinkin ⋅ Aleksandr Beznosikov

Minimizing Functions Close to Submodularity

Haruto Konno ⋅ Shinji Ito

Target-ESS Tempered Policy Optimization (TETPO): Smooth Variance Control via Bridge Importance Sampling

Shayan Mohajer Hamidi ⋅ Kayhan Behdin ⋅ Wenhui Zhu ⋅ Aida Rahmattalabi ⋅ Jincheng Cao ⋅ Jelena Markovic-Voronov ⋅ Alborz Geramifard

Edge of Stability Occurs in Minimax Optimization

Yejun Kim ⋅ Dongchan Shin ⋅ Donghwan Kim

The Local Geometry of Magnitude and Direction Decoupling

Chenxiang Zhang ⋅ Kai Lion ⋅ Florian Hübler ⋅ Jun Pang ⋅ Antonio Orvieto

Code-to-Harness: Distilling Black-Box Optimizers from Self-Play

Yi Wu ⋅ Zheng Ren ⋅ Zhiyu Hu ⋅ Haochen Wang ⋅ Daryl Chang ⋅ Li Wei ⋅ Ting Wang ⋅ Zhen Li ⋅ Pooja Gupta ⋅ Nitin Jindal ⋅ Lukasz Heldt

Projected Hessian Direction Estimation by Comparisons under Holder Smoothness

Liyao Chang

When Acceleration Breaks: (Stochastic) Edges of Stability in Normalized SGD

Itay Lavie ⋅ Clarissa Lauditi ⋅ Cengiz Pehlevan

The Cleaning Layer: How the Convolution Bias on Task-Irrelevant Positions Inflates Curvature and Gradient Noise

Andreas Horlbeck ⋅ Adrian Krenzer

Provable Edge-of-Stability for Adam on a One-Dimensional Quadratic

Yiman Fong ⋅ Heng Yang

A Dual Method for Outer-Regularized Wasserstein Barycenters with Exact Transport Costs

Ivan Zhytkevych ⋅ Denys Ruban ⋅ Augusto Gerolin

What Is Richer Optimization Geometry Worth? Hessian-Blind Pricing of Structured Preconditioners

Yutian Chu

VENUS: Decoupling the Samples in MARS Benefits Small-Batch Training

Igor Sokolov ⋅ Yassine Maziane ⋅ Yury Demidovich ⋅ Peter Richtarik ⋅ Egor Shulgin

Multiplicative vs. Additive State Coupling in Learned Optimizer Schedules

M. Harper Langston ⋅ Pierre-David Letourneau ⋅ Dalton Jones ⋅ Roland Memisevic ⋅ Peter Scott ⋅ Mingu Lee ⋅ Harris Teague ⋅ Richard A Lethin

Physical Muon: Orthogonalization as an Equilibrium Computation

Yuren Hao

Guarded Block Transfers for Polytope Distance: Linear Convergence with Explicit Constants and Gap-Certified Screening for SVM Training

mayank gupta

When to use what Schatten-$p$ norm in deep learning?

Thomas Pethick

AdaSign: Turning 1-Bit Worker Votes into Adaptive Updates

Xiaoyuan Liang ⋅ Sebastian Loeschcke ⋅ Thorsten Kurth ⋅ Mads Toftrup ⋅ Boris Bonev ⋅ Animashree Anandkumar

Can Muon Adapt Its Stepsize Without Knowing the Solution Distance?

Yury Demidovich ⋅ Abhishek Chakraborty ⋅ Grigory Malinovsky ⋅ Angelia Nedich ⋅ Peter Richtarik

Learning Complementary Modes for Pareto Set Optimization

Yuqing Wu ⋅ Zishun Yu ⋅ Xinhua Zhang

Does Muon's Pretraining Advantage Over Adam Survive Fine-Tuning?

Glory Bagai ⋅ Jonas Geiping ⋅ Antonio Orvieto

An Update Noise Scale for Stateful Optimizers

Param Mody ⋅ Mark Schmidt

A Radial Smoothness Model for LMO-Based Optimization

Sam Laing ⋅ Egor Shulgin ⋅ Antonio Orvieto ⋅ Peter Richtarik

Primal-Dual Adaptive Subgradient Methods

Karthik Prakhya ⋅ Zimeng Wang ⋅ Alp Yurtsever

Sample Complexity of On-Policy RLVR Algorithms: A Generic Analysis using Non-Uniform Smoothness and Aligned Features

Quan Nguyen ⋅ Sharan Vaswani ⋅ Christos Thrampoulidis

Anytime Convergence via Interpolation Annealing in Schedule-Free Optimization

Jiseok Chae

LoRA-TSD: Tangent-Space Spectral Descent for LoRA via Muon-Style Updates

Dmitrii Andriianov ⋅ Andrey Veprikov ⋅ Aleksandr Beznosikov

Sign compression for Muon: SignMuon, MuonSign, and the Limits of Error Feedback

Maria Smirnova ⋅ Alexey Kravatskiy

Graph Coarsening Enables Escaping Local Optima in Nonconvex MAX-CUT

M. Harper Langston ⋅ Pierre-David Letourneau ⋅ Dalton Jones ⋅ Peter Scott ⋅ Roland Memisevic ⋅ Mingu Lee ⋅ Harris Teague ⋅ Richard A Lethin

When Does Pruning Earn Its Optimization Cost? A Selection-Valid PAC–Bayes Diagnostic for Frontier Optimizers

Ahanaf Ariq

Critical Points of Linear Self-Attention with Quadratic Loss on a Single Training Example

Ava Berenji ⋅ Khang Nguyen ⋅ Guido Montufar

Aligning Task Gradients to a Frozen Encoder: Regularizing Semi-supervised Segmentation Without Freezing

Yakov Danishevsky

Shallow ReLU Classifiers on Non-Linearly Separable Data: The Loss Landscape, Edge of Stability, and Beyond

Quan Nguyen ⋅ Robin Yadav ⋅ Param Mody ⋅ Mark Schmidt

Asymptotic Regret Bounds for Multi-Task Linear Bandits with Shared Low-Rank Structure

SHIUH CHYNG CHENG ⋅ Po-An Wang

Beyond Loss Gaps: Stability and Geometry in Dynamic Sample Reweighting

Chulhee Yun ⋅ Ananda Theertha Suresh

TorchTangents: An Accessible Bridge for Architecture-Preconditioned Optimizers

Joshua DeOliveira ⋅ Elke A. Rundensteiner

Pretrain-Then-Calibrate: Reliable Contextual Optimization Along a Solution Path

Haixiang Lan ⋅ Tianyu Wang ⋅ Henry Lam

Distributed Linear Programming on GPU Clusters at Extreme Scale

Arnaud Deza ⋅ Santanu Dey ⋅ Pascal Van Hentenryck

Spike timing and environment dependent optimisation

Ismaeel Ramzan

Zero-Order Optimization via Learnable Direction Sampling

Valery Parfenov ⋅ Grigoriy Evseev ⋅ Andrey Veprikov ⋅ Nikolay Bushkov ⋅ Stanislav Moiseev ⋅ Aleksandr Beznosikov

Averaged Mirror Descent: a Convergent Algorithm for Entropic Gromov–Wasserstein Problems

Joanna Marks ⋅ Gabriel Rioux ⋅ Riccardo Passeggeri

NGN-Scion: Making Norm-Constrained LMO Optimizers Robust to the Learning Rate

Arman Bolatov ⋅ Rustem Islamov ⋅ Eduard Gorbunov ⋅ Antonio Orvieto ⋅ Sebastian Stich ⋅ Martin Takac

AdaGrad and Universality in Composite Optimization: Failure and a Remedy

Matia Bojovic ⋅ Saverio Salzo ⋅ Massimiliano Pontil

Same Training Loss, Different Recovery: Optimizer-Dependent Solution Selection in Matrix Sensing

Luca Stümper ⋅ Antonio Orvieto

The Phase Transition in Random Reshuffling: Tight Rates under Strong Convexity

Yujun Kim ⋅ Jaeyoung Cha ⋅ Chulhee Yun

Lower Bounds for $(L_0,L_1)$-Smooth Optimization

Egor Shulgin ⋅ Abdurakhmon Sadiev

Rennala MVR: Improved Time Complexity for Parallel Stochastic Optimization via Momentum Variance Reduction

Zhirayr Tovmasyan ⋅ Artavazd Maranjyan ⋅ Peter Richtarik

Closure Masks for Hardware-Compatible 2:4 Sparse Muon

Doyoon Kim ⋅ Namhoon Lee

Ember: A Kilobyte-State Optimizer for Token Interfaces

Kathan Shah

Differentially Private Clipping-Free Stochastic Sign Descent

Alexey Kravatskiy ⋅ Anton Pliusnin ⋅ Savelii Chezhegov ⋅ Aleksandr Shestakov ⋅ Daniil Medyakov ⋅ Aleksandr Beznosikov

Partially Informed Stochastic Optimization via Zeroth-Order Residual Tracking

El Mahdi Chayti ⋅ Alireza Mirrokni ⋅ Martin Jaggi

Power Steepest Mirror Flow: Disentangling Mirror and Steepest Geometries in Deep Linear Networks

Mohammad Moshtaghifar ⋅ Connall Garrod ⋅ Mark Schmidt ⋅ Christos Thrampoulidis

Data-Dependent Robust Termination of First-Order Methods for Support Vector Machines

Matthew Hough ⋅ Stephen Vavasis

Memory-Regularized Forward–Reverse Layer-wise Optimization

Ali Ghobadzadeh ⋅ Sayyed H Moghaddam ⋅ SAEED GAZOR

Geometric Algorithms for Differentially Private Combinatorial Optimization with Constraints

Akbar Rafiey