Optimization

Unconstrained Dynamic Regret via Sparse Coding NeurIPS 2023 Understanding and Bridging the Modality Gap for Speech Translation ACL 2023 Understanding and Generalizing Contrastive Learning from the Inverse Optimal Transport Perspective ICML 2023 Understanding Contrastive Learning via Distributionally Robust Optimization NeurIPS 2023 Understanding Edge-of-Stability Training Dynamics with a Minimalist Example ICLR 2023 Understanding Gradient Regularization in Deep Learning: Efficient Finite-Difference Computation and Implicit Bias ICML 2023 Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization NeurIPS 2023 Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks NeurIPS 2023 Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers NeurIPS 2023 Understanding Self-attention Mechanism via Dynamical System Perspective ICCV 2023 Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization ICLR 2023 Unexpected Improvements to Expected Improvement for Bayesian Optimization NeurIPS 2023 Unfolding Framework with Prior of Convolution-Transformer Mixture and Uncertainty Estimation for Video Snapshot Compressive Imaging ICCV 2023 Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems NeurIPS 2023 Unifying Nesterov’s Accelerated Gradient Methods for Convex and Strongly Convex Objective Functions ICML 2023 Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks CVPR 2023 Unit Scaling: Out-of-the-Box Low-Precision Training ICML 2023 Universal Adaptive Data Augmentation IJCAI 2023 Universal Deep Image Compression via Content-Adaptive Optimization With Adapters WACV 2023 Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization NeurIPS 2023 Universality of Langevin Diffusion for Private Optimization, with Applications to Sampling from Rashomon Sets COLT 2023 Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach NeurIPS 2023 Universal Physics-Informed Neural Networks: Symbolic Differential Operator Discovery with Sparse Data ICML 2023 Unlearnable Clusters: Towards Label-Agnostic Unlearnable Examples CVPR 2023 Unleashing the Potential of Spiking Neural Networks with Dynamic Confidence ICCV 2023