Neural Network Optimization

Implicit Bias in Noisy-SGD: With Applications to Differentially Private Training AISTATS 2024 Implicit Compressibility of Overparametrized Neural Networks Trained with Heavy-Tailed SGD ICML 2024 Implicit Optimization Bias of Next-token Prediction in Linear Models NeurIPS 2024 Implicit Regularization in Deep Tucker Factorization: Low-Rankness via Structured Sparsity AISTATS 2024 Implicit regularization of deep residual networks towards neural ODEs ICLR 2024 Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems NeurIPS 2024 Implicit Regularization Paths of Weighted Neural Representations NeurIPS 2024 Improved Implicit Neural Representation with Fourier Reparameterized Training CVPR 2024 Improving Adaptive Online Learning Using Refined Discretization ALT 2024 Improving Adaptivity via Over-Parameterization in Sequence Models NeurIPS 2024 Improving Convergence and Generalization Using Parameter Symmetries ICLR 2024 Improving Deep Learning Optimization through Constrained Parameter Regularization NeurIPS 2024 Improving equilibrium propagation without weight symmetry through Jacobian homeostasis ICLR 2024 Improving Equivariant Model Training via Constraint Relaxation NeurIPS 2024 Improving Generalization and Convergence by Enhancing Implicit Regularization NeurIPS 2024 Improving Neural Network Generalization on Data-Limited Regression with Doubly-Robust Boosting AAAI 2024 Improving Neural ODE Training with Temporal Adaptive Batch Normalization NeurIPS 2024 Improving Noise Robustness in Self-supervised Pre-trained Model for Speaker Verification Interspeech 2024 Improving SAM Requires Rethinking its Optimization Formulation ICML 2024 Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting NeurIPS 2024 Improving Training Efficiency of Diffusion Models via Multi-Stage Framework and Tailored Multi-Decoder Architecture CVPR 2024 InceptionNeXt: When Inception Meets ConvNeXt CVPR 2024 In-Context Former: Lightning-fast Compressing Context for Large Language Model EMNLP 2024 In-context Learning and Gradient Descent Revisited NAACL 2024 In-Context Learning with Representations: Contextual Generalization of Trained Transformers NeurIPS 2024