neural network training

nnScaler: Constraint-Guided Parallelization Plan Generation for Deep Learning Training OSDI 2024 One Forward is Enough for Neural Network Training via Likelihood Ratio Method ICLR 2024 On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm CVPR 2024 On the Variance of Neural Network Training with respect to Test Sets and Distributions ICLR 2024 Optical Diffusion Models for Image Generation NeurIPS 2024 Random Linear Projections Loss for Hyperplane-Based Optimization in Neural Networks UAI 2024 Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations NeurIPS 2024 Scaling physics-informed hard constraints with mixture-of-experts ICLR 2024 SimPSI: A Simple Strategy to Preserve Spectral Information in Time Series Data Augmentation AAAI 2024 Swift Sampler: Efficient Learning of Sampler by 10 Parameters NeurIPS 2024 Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks NeurIPS 2024 Taming Binarized Neural Networks and Mixed-Integer Programs AAAI 2024 Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms NeurIPS 2024 Topological obstruction to the training of shallow ReLU neural networks NeurIPS 2024 Towards Learning and Explaining Indirect Causal Effects in Neural Networks AAAI 2024 Towards training digitally-tied analog blocks via hybrid gradient computation NeurIPS 2024 Waxing-and-Waning: a Generic Similarity-based Framework for Efficient Self-Supervised Learning ICLR 2024 Weight-Sharing Regularization AISTATS 2024 When to Grow? A Fitting Risk-Aware Policy for Layer Growing in Deep Neural Networks AAAI 2024 Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats ICLR 2023 A Computationally Efficient Sparsified Online Newton Method NeurIPS 2023 A Mini-Block Fisher Method for Deep Neural Networks AISTATS 2023 An Inexact Augmented Lagrangian Algorithm for Training Leaky ReLU Neural Network with Group Sparsity JMLR 2023 ARK: GPU-driven Code Execution for Distributed Deep Learning NSDI 2023 ASkewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks AISTATS 2023