Optimization

Tensor Compressive Sensing Fused Low-Rankness and Local-Smoothness AAAI 2023 The Implicit Bias of Batch Normalization in Linear Models and Two-layer Linear Convolutional Neural Networks COLT 2023 The Implicit Regularization of Momentum Gradient Descent in Overparametrized Models AAAI 2023 Time-synchronous one-pass Beam Search for Parallel Online and Offline Transducers with Dynamic Block Training Interspeech 2023 Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition CVPR 2023 Towards Understanding Ensemble Distillation in Federated Learning ICML 2023 Transcending Scaling Laws with 0.1% Extra Compute EMNLP 2023 Transformer-Based Learned Optimization CVPR 2023 Tunable Convolutions With Parametric Multi-Loss Optimization CVPR 2023 Two Losses Are Better Than One: Faster Optimization Using a Cheaper Proxy ICML 2023 Understanding Incremental Learning of Gradient Descent: A Fine-grained Analysis of Matrix Sensing ICML 2023 Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization NeurIPS 2023 User-Controllable Arbitrary Style Transfer via Entropy Regularization AAAI 2023 VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization CVPR 2023 Wavelet Diffusion Models Are Fast and Scalable Image Generators CVPR 2023 Why (and When) does Local SGD Generalize Better than SGD? ICLR 2023 Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient Algorithms ICLR 2023 You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model CVPR 2023 Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation ICLR 2023 3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation ICML 2022 8-bit Optimizers via Block-wise Quantization ICLR 2022 Accelerated Federated Learning with Decoupled Adaptive Optimization ICML 2022 Accelerated Gradient Methods for Geodesically Convex Optimization: Tractable Algorithms and Convergence Analysis ICML 2022 Accelerated Primal-Dual Gradient Method for Smooth and Convex-Concave Saddle-Point Problems with Bilinear Coupling NeurIPS 2022 A Communication-Efficient Distributed Gradient Clipping Algorithm for Training Deep Neural Networks NeurIPS 2022