Optimization & Theory

SGD with Large Step Sizes Learns Sparse Features ICML 2023 Shakes on a Plane: Unsupervised Depth Estimation From Unstabilized Photography CVPR 2023 Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers EACL 2023 SHARCS: Efficient Transformers Through Routing with Dynamic Width Sub-networks EMNLP 2023 Sharpness-Aware Minimization Leads to Low-Rank Features NeurIPS 2023 ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer NeurIPS 2023 Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations CVPR 2023 Simple Hardware-Efficient Long Convolutions for Sequence Modeling ICML 2023 Simplex Random Features ICML 2023 Simplicity Bias in Transformers and their Ability to Learn Sparse Boolean Functions ACL 2023 Simplifying Momentum-based Positive-definite Submanifold Optimization with Applications to Deep Learning ICML 2023 Singularformer: Learning to Decompose Self-Attention to Linearize the Complexity of Transformer IJCAI 2023 SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization CVPR 2023 SLAMB: Accelerated Large Batch Training with Sparse Communication ICML 2023 Sliced Optimal Partial Transport CVPR 2023 Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention CVPR 2023 SlowBERT: Slow-down Attacks on Input-adaptive Multi-exit BERT ACL 2023 Small batch deep reinforcement learning NeurIPS 2023 SmoothHess: ReLU Network Feature Interactions via Stein's Lemma NeurIPS 2023 Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models NeurIPS 2023 SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models ICML 2023 SMPConv: Self-Moving Point Representations for Continuous Convolution CVPR 2023 SOL: Sampling-based Optimal Linear bounding of arbitrary scalar functions NeurIPS 2023 Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective CVPR 2023 Some Might Say All You Need Is Sum IJCAI 2023