Optimization & Theory

Speed Up Object Detection on Gigapixel-Level Images With Patch Arrangement CVPR 2022 SpikeConverter: An Efficient Conversion Framework Zipping the Gap between Artificial Neural Networks and Spiking Neural Networks AAAI 2022 Spline-PINN: Approaching PDEs without Data Using Fast, Physics-Informed Hermite-Spline CNNs AAAI 2022 Squeezeformer: An Efficient Transformer for Automatic Speech Recognition NeurIPS 2022 Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers NeurIPS 2022 STGN: an Implicit Regularization Method for Learning with Noisy Labels in Natural Language Processing EMNLP 2022 Stochastic Adaptive Activation Function NeurIPS 2022 Stochastic DCA with Variance Reduction and Applications in Machine Learning JMLR 2022 Stochastic Second-Order Methods Improve Best-Known Sample Complexity of SGD for Gradient-Dominated Functions NeurIPS 2022 Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability CVPR 2022 Structural Pruning via Latency-Saliency Knapsack NeurIPS 2022 Structured Pruning Learns Compact and Accurate Models ACL 2022 Subspace Adversarial Training CVPR 2022 Super-Acceleration with Cyclical Step-sizes AISTATS 2022 Surprising Instabilities in Training Deep Networks and a Theoretical Analysis NeurIPS 2022 Surrogate Gap Minimization Improves Sharpness-Aware Training ICLR 2022 SVT-Net: Super Light-Weight Sparse Voxel Transformer for Large Scale Place Recognition AAAI 2022 SwapMix: Diagnosing and Regularizing the Over-Reliance on Visual Context in Visual Question Answering CVPR 2022 Symbolic Distillation for Learned TCP Congestion Control NeurIPS 2022 Synergy and Symmetry in Deep Learning: Interactions between the Data, Model, and Inference Algorithm ICML 2022 TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets NeurIPS 2022 TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training NeurIPS 2022 Taylor-Lagrange Neural Ordinary Differential Equations: Toward Fast Training and Evaluation of Neural ODEs IJCAI 2022 Teach Less, Learn More: On the Undistillable Classes in Knowledge Distillation NeurIPS 2022 Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction NeurIPS 2022