Optimization & Theory

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery NeurIPS 2023 Head-Free Lightweight Semantic Segmentation with Linear Transformer AAAI 2023 HiFi: High-Information Attention Heads Hold for Parameter-Efficient Model Adaptation ACL 2023 High Probability Convergence of Stochastic Gradient Methods ICML 2023 Honey, I Shrunk the Language: Language Model Behavior at Reduced Scale. ACL 2023 HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search CVPR 2023 How Can Objects Help Action Recognition? CVPR 2023 How Does Information Bottleneck Help Deep Learning? ICML 2023 How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization ICLR 2023 How much does Initialization Affect Generalization? ICML 2023 How Powerful are Shallow Neural Networks with Bandlimited Random Weights? ICML 2023 How Predictable Are Large Language Model Capabilities? A Case Study on BIG-bench EMNLP 2023 How to Distill your BERT: An Empirical Study on the Impact of Weight Initialisation and Distillation Objectives ACL 2023 Hybrid Inverted Index Is a Robust Accelerator for Dense Retrieval EMNLP 2023 Hybrid Pixel-Unshuffled Network for Lightweight Image Super-resolution AAAI 2023 Hyena Hierarchy: Towards Larger Convolutional Language Models ICML 2023 HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition Interspeech 2023 HyperJump: Accelerating HyperBand via Risk Modelling AAAI 2023 HyperMixer: An MLP-based Low Cost Alternative to Transformers ACL 2023 HyperPELT: Unified Parameter-Efficient Language Model Tuning for Both Language and Vision-and-Language Tasks ACL 2023 HyperReel: High-Fidelity 6-DoF Video With Ray-Conditioned Sampling CVPR 2023 ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing CVPR 2023 ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification NeurIPS 2023 ImbSAM: A Closer Look at Sharpness-Aware Minimization in Class-Imbalanced Recognition ICCV 2023 Impact of classification difficulty on the weight matrices spectra in Deep Learning and application to early-stopping JMLR 2023