Neural Network Optimization

Memorization Capacity of Neural Networks with Conditional Computation ICLR 2023 Memory Efficient Optimizers with 4-bit States NeurIPS 2023 Meta-AdaM: An Meta-Learned Adaptive Optimizer with Momentum for Few-Shot Learning NeurIPS 2023 Meta-Learning Online Adaptation of Language Models EMNLP 2023 Meta-Learning with Adjoint Methods AISTATS 2023 Mind the (optimality) Gap: A Gap-Aware Learning Rate Scheduler for Adversarial Nets AISTATS 2023 Minimum norm interpolation by perceptra: Explicit regularization and implicit bias NeurIPS 2023 Minimum Variance Unbiased N:M Sparsity for the Neural Gradients ICLR 2023 Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals NeurIPS 2023 Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction Interspeech 2023 MixCE: Training Autoregressive Language Models by Mixing Forward and Reverse Cross-Entropies ACL 2023 MixPath: A Unified Approach for One-shot Neural Architecture Search ICCV 2023 MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates NeurIPS 2023 MMNMT: Modularizing Multilingual Neural Machine Translation with Flexibly Assembled MoE and Dense Blocks EMNLP 2023 Modeling Stroke Mask for End-to-End Text Erasing WACV 2023 ModelKeeper: Accelerating DNN Training via Automated Training Warmup NSDI 2023 Modelling the Reduplicating Lushootseed Morphology with an FST and LSTM ACL 2023 Modulated Neural ODEs NeurIPS 2023 Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions ICML 2023 Momentum Provably Improves Error Feedback! NeurIPS 2023 Most Neural Networks Are Almost Learnable NeurIPS 2023 MSINet: Twins Contrastive Search of Multi-Scale Interaction for Object ReID CVPR 2023 Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives NeurIPS 2023 Network Expansion for Practical Training Acceleration CVPR 2023 Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models ACL 2023