Neural Network Optimization

RNAS-MER: A Refined Neural Architecture Search With Hybrid Spatiotemporal Operations for Micro-Expression Recognition WACV 2023 Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond AISTATS 2023 Robustly Learning a Single Neuron via Sharpness ICML 2023 Robust Mean Teacher for Continual and Gradual Test-Time Adaptation CVPR 2023 Robust Object Modeling for Visual Tracking ICCV 2023 ROME: Robustifying Memory-Efficient NAS via Topology Disentanglement and Gradient Accumulation ICCV 2023 SAAL: Sharpness-Aware Active Learning ICML 2023 Saddle-to-Saddle Dynamics in Diagonal Linear Networks NeurIPS 2023 SAM operates far from home: eigenvalue regularization as a dynamical phenomenon ICML 2023 Samples With Low Loss Curvature Improve Data Efficiency CVPR 2023 Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks JMLR 2023 Scaling Laws for Discriminative Speech Recognition Rescoring Models Interspeech 2023 Scaling Laws for Multilingual Neural Machine Translation ICML 2023 Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer NeurIPS 2023 Scattering Vision Transformer: Spectral Mixing Matters NeurIPS 2023 SCI: A Spectrum Concentrated Implicit Neural Compression for Biomedical Data AAAI 2023 Searching Efficient Neural Architecture With Multi-Resolution Fusion Transformer for Appearance-Based Gaze Estimation WACV 2023 Searching for Robust Binary Neural Networks via Bimodal Parameter Perturbation WACV 2023 Search Query Spell Correction with Weak Supervision in E-commerce ACL 2023 Second-order regression models exhibit progressive sharpening to the edge of stability ICML 2023 SEENN: Towards Temporal Spiking Early Exit Neural Networks NeurIPS 2023 Segmented Recurrent Transformer: An Efficient Sequence-to-Sequence Model EMNLP 2023 Self-Attentive Pooling for Efficient Deep Learning WACV 2023 Sensitivity-Aware Visual Parameter-Efficient Fine-Tuning ICCV 2023 Separable Physics-Informed Neural Networks NeurIPS 2023