Continuous Optimization

Span-Agnostic Optimal Sample Complexity and Oracle Inequalities for Average-Reward RL COLT 2025 Sparse SVM with Hard-Margin Loss: a Newton-Augmented Lagrangian Method in Reduced Dimensions JMLR 2025 Speedup Techniques for Switchable Temporal Plan Graph Optimization AAAI 2025 SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video CVPR 2025 Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization ICML 2025 Stability and Generalization Analysis of Decentralized SGD: Sharper Bounds Beyond Lipschitzness and Smoothness ICML 2025 Stacey: Promoting Stochastic Steepest Descent via Accelerated ℓ_p-Smooth Nonconvex Optimization ICML 2025 State-Compute Replication: Parallelizing High-Speed Stateful Packet Processing NSDI 2025 Statistical Advantages of Perturbing Cosine Router in Mixture of Experts ICLR 2025 Statistical and Computational Guarantees of Kernel Max-Sliced Wasserstein Distances ICML 2025 Statistical Inference of Constrained Stochastic Optimization via Sketched Sequential Quadratic Programming JMLR 2025 Statistical Query Hardness of Multiclass Linear Classification with Random Classification Noise ICML 2025 Stochastic Gradient Estimation for Higher-Order Differentiable Rendering ICCV 2025 Stochastic Interior-Point Methods for Smooth Conic Optimization with Applications JMLR 2025 Stochastic Smoothed Primal-Dual Algorithms for Nonconvex Optimization with Linear Inequality Constraints ICML 2025 Structure-informed Risk Minimization for Robust Ensemble Learning ICML 2025 Taking a Big Step: Large Learning Rates in Denoising Score Matching Prevent Memorization COLT 2025 Temperature-Annealed Boltzmann Generators ICML 2025 The Adaptive Complexity of Finding a Stationary Point COLT 2025 The Butterfly Effect: Neural Network Training Trajectories Are Highly Sensitive to Initial Conditions ICML 2025 The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation ICCV 2025 The Global Convergence Time of Stochastic Gradient Descent in Non-Convex Landscapes: Sharp Estimates via Large Deviations ICML 2025 Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport ICML 2025 The Planted Spanning Tree Problems: Exact Overlap Characterization via Local Weak Convergence Extended Abstract COLT 2025 The Power of Random Features and the Limits of Distribution-Free Gradient Descent ICML 2025