Optimization

Fast, Differentiable and Sparse Top-k: a Convex Analysis Perspective ICML 2023 Faster Projection-Free Augmented Lagrangian Methods via Weak Proximal Oracle AISTATS 2023 Faster Rates of Convergence to Stationary Points in Differentially Private Optimization ICML 2023 Fast Objective & Duality Gap Convergence for Non-Convex Strongly-Concave Min-Max Problems with PL Condition JMLR 2023 FedAvg Converges to Zero Training Loss Linearly for Overparameterized Multi-Layer Neural Networks ICML 2023 FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits CVPR 2023 FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference ACL 2023 FRA-RIR: Fast Random Approximation of the Image-source Method Interspeech 2023 From high-dimensional & mean-field dynamics to dimensionless ODEs: A unifying approach to SGD in two-layers networks COLT 2023 Gaussian Mixture Solvers for Diffusion Models NeurIPS 2023 Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation CVPR 2023 Generalized Differentiable RANSAC ICCV 2023 GeoLS: Geodesic Label Smoothing for Image Segmentation MIDL 2023 Global Convergence of Over-parameterized Deep Equilibrium Models AISTATS 2023 Global Convergence of Sub-gradient Method for Robust Matrix Recovery: Small Initialization, Noisy Measurements, and Over-parameterization JMLR 2023 Global optimality for Euclidean CCCP under Riemannian convexity ICML 2023 Gold Doesn’t Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information EACL 2023 Gradient Descent Converges Linearly for Logistic Regression on Separable Data ICML 2023 Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks ICML 2023 Gradient Descent Monotonically Decreases the Sharpness of Gradient Flow Solutions in Scalar Networks and Beyond ICML 2023 Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy NeurIPS 2023 High Probability Convergence of Stochastic Gradient Methods ICML 2023 HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search CVPR 2023 How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench EMNLP 2023 ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing CVPR 2023