Optimization

Meta-Learning with Adjoint Methods AISTATS 2023 Minimizing the Accumulated Trajectory Error To Improve Dataset Distillation CVPR 2023 Minimizing Trajectory Curvature of ODE-based Generative Models ICML 2023 Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach ICLR 2023 Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling AAAI 2023 Moccasin: Efficient Tensor Rematerialization for Neural Networks ICML 2023 MODeL: Memory Optimizations for Deep Learning ICML 2023 Multi-View Reconstruction Using Signed Ray Distance Functions (SRDF) CVPR 2023 Neural Fields with Hard Constraints of Arbitrary Differential Order NeurIPS 2023 Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might Be ICLR 2023 NVTC: Nonlinear Vector Transform Coding CVPR 2023 ObjectMatch: Robust Registration Using Canonical Object Correspondences CVPR 2023 OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models ICML 2023 On amortizing convex conjugates for optimal transport ICLR 2023 On Enhancing Fine-Tuning for Pre-trained Language Models EMNLP 2023 On Learning Rates and Schrödinger Operators JMLR 2023 On quantum backpropagation, information reuse, and cheating measurement collapse NeurIPS 2023 On the Convergence of AdaGrad(Norm) on R^d: Beyond Convexity, Non-Asymptotic Rate and Acceleration ICLR 2023 On the Convergence of Gradient Flow on Multi-layer Linear Models ICML 2023 On the Dynamics Under the Unhinged Loss and Beyond JMLR 2023 On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data AISTATS 2023 On the Training Instability of Shuffling SGD with Batch Normalization ICML 2023 Optimal Convergence Rates for Agnostic Nyström Kernel Learning ICML 2023 Optimal Sets and Solution Paths of ReLU Networks ICML 2023 Optimal Shrinkage for Distributed Second-Order Optimization ICML 2023