Neural Network Optimization

The Mystery of the Pathological Path-star Task for Language Models EMNLP 2024 The Open-World Lottery Ticket Hypothesis for OOD Intent Classification COLING 2024 Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach ICLR 2024 Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks NeurIPS 2024 The Orthogonality of Weight Vectors: The Key Characteristics of Normalization and Residual Connections IJCAI 2024 There Are No Shortcuts to Anywhere Worth Going: Identifying Shortcuts in Deep Learning Models for Medical Image Analysis MIDL 2024 The Road Less Scheduled NeurIPS 2024 The Role of Over-Parameterization in Machine Learning – the Good, the Bad, the Ugly AAAI 2024 Think before you speak: Training Language Models With Pause Tokens ICLR 2024 Tight and Efficient Upper Bound on Spectral Norm of Convolutional Layers ECCV 2024 Tight Convergence Rate Bounds for Optimization Under Power Law Spectral Conditions JMLR 2024 Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective NeurIPS 2024 Tokenization Falling Short: On Subword Robustness in Large Language Models EMNLP 2024 Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics NeurIPS 2024 Towards Better Structured Pruning Saliency by Reorganizing Convolution WACV 2024 Towards Effective and Efficient Non-autoregressive Decoding Using Block-based Attention Mask Interspeech 2024 Towards Efficient Training and Evaluation of Robust Models against l_0 Bounded Adversarial Perturbations ICML 2024 Towards Explainable Monaural Speaker Separation with Auditory-based Training Interspeech 2024 Towards Geometric Normalization Techniques in SE(3) Equivariant Graph Neural Networks for Physical Dynamics Simulations IJCAI 2024 Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner CVPR 2024 Towards Robust Extractive Question Answering Models: Rethinking the Training Methodology EMNLP 2024 Towards Robust Learning to Optimize with Theoretical Guarantees CVPR 2024 Towards the Dynamics of a DNN Learning Symbolic Interactions NeurIPS 2024 Towards training digitally-tied analog blocks via hybrid gradient computation NeurIPS 2024 Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion ICLR 2024