neural network optimization

Layer-wise linear mode connectivity ICLR 2024 LEAD: Exploring Logit Space Evolution for Model Selection CVPR 2024 LF-ViT: Reducing Spatial Redundancy in Vision Transformer for Efficient Image Recognition AAAI 2024 Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning ACL 2024 Lightweight Transducer Based on Frame-Level Criterion Interspeech 2024 Linear-Complexity Self-Supervised Learning for Speech Processing Interspeech 2024 Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts ICLR 2024 LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems NeurIPS 2024 Lossless Acceleration of Large Language Model via Adaptive N-gram Parallel Decoding NAACL 2024 Masked Structural Growth for 2x Faster Language Model Pre-training ICLR 2024 Matching the Statistical Query Lower Bound for k-Sparse Parity Problems with Sign Stochastic Gradient Descent NeurIPS 2024 MaxQ: Multi-Axis Query for N:M Sparsity Network CVPR 2024 MCNet: Rethinking the Core Ingredients for Accurate and Efficient Homography Estimation CVPR 2024 Memory-Efficient LLM Training with Online Subspace Descent NeurIPS 2024 MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence NeurIPS 2024 Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes NeurIPS 2024 MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts NeurIPS 2024 MQuinE: a Cure for “Z-paradox” in Knowledge Graph Embedding EMNLP 2024 Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks NeurIPS 2024 Neural Network Reparametrization for Accelerated Optimization in Molecular Simulations NeurIPS 2024 Noise-Free Optimization in Early Training Steps for Image Super-resolution AAAI 2024 Non-asymptotic Convergence of Training Transformers for Next-token Prediction NeurIPS 2024 Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks NeurIPS 2024 Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers NeurIPS 2024 On the Foundations of Shortcut Learning ICLR 2024