Optimization & Theory

Principled Acceleration of Iterative Numerical Methods Using Machine Learning ICML 2023 Principled Weight Initialisation for Input-Convex Neural Networks NeurIPS 2023 Private Federated Learning with Autotuned Compression ICML 2023 Probability-Based Global Cross-Modal Upsampling for Pansharpening CVPR 2023 Progressive Ensemble Distillation: Building Ensembles for Efficient Inference NeurIPS 2023 Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation CVPR 2023 Prompting is not a substitute for probability measurements in large language models EMNLP 2023 Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs NeurIPS 2023 Provable Data Subset Selection For Efficient Neural Networks Training ICML 2023 Provable Dynamic Fusion for Low-Quality Multimodal Data ICML 2023 Provable Memorization Capacity of Transformers ICLR 2023 Provably and Practically Efficient Neural Contextual Bandits ICML 2023 Proximal Stochastic Recursive Momentum Methods for Nonconvex Composite Decentralized Optimization AAAI 2023 ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-Cost Proxies AAAI 2023 Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge CVPR 2023 Pruning Pre-trained Language Models with Principled Importance and Self-regularization ACL 2023 Pseudointelligence: A Unifying Lens on Language Model Evaluation EMNLP 2023 PuMer: Pruning and Merging Tokens for Efficient Vision Language Models ACL 2023 Q-DETR: An Efficient Low-Bit Quantized Detection Transformer CVPR 2023 Quantized Feature Distillation for Network Quantization AAAI 2023 Quantum Multi-Model Fitting CVPR 2023 Quantum Ridgelet Transform: Winning Lottery Ticket of Neural Networks with Quantum Computation ICML 2023 Query-Aware Quantization for Maximum Inner Product Search AAAI 2023 Randomized Positional Encodings Boost Length Generalization of Transformers ACL 2023 RDumb: A simple approach that questions our progress in continual test-time adaptation NeurIPS 2023