Optimization & Theory

Towards Efficient Simultaneous Speech Translation: CUNI-KIT System for Simultaneous Track at IWSLT 2023 ACL 2023 Towards Fully Quantized Neural Networks For Speech Enhancement Interspeech 2023 Towards Inference Efficient Deep Ensemble Learning AAAI 2023 Towards Inferential Reproducibility of Machine Learning Research ICLR 2023 Towards Real-Time Segmentation on the Edge AAAI 2023 Towards Robust Pruning: An Adaptive Knowledge-Retention Pruning Strategy for Language Models EMNLP 2023 Towards Sustainable Learning: Coresets for Data-efficient Deep Learning ICML 2023 Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities NeurIPS 2023 Towards Understanding and Improving Knowledge Distillation for Neural Machine Translation ACL 2023 Towards Understanding Ensemble Distillation in Federated Learning ICML 2023 Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models NeurIPS 2023 Training a General Spiking Neural Network with Improved Efficiency and Minimum Latency ACML 2023 Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete NeurIPS 2023 Training Meta-Surrogate Model for Transferable Adversarial Attack AAAI 2023 Training Neural Networks is NP-Hard in Fixed Dimension NeurIPS 2023 Training Transformers with 4-bit Integers NeurIPS 2023 Training Your Image Restoration Network Better with Random Weight Network as Optimization Function NeurIPS 2023 Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks NeurIPS 2023 TRAMS: Training-free Memory Selection for Long-range Language Modeling EMNLP 2023 Transcending Scaling Laws with 0.1% Extra Compute EMNLP 2023 Transfer Learning Enhanced DeepONet for Long-Time Prediction of Evolution Equations AAAI 2023 Transformer-Based Learned Optimization CVPR 2023 Transformer Language Models Handle Word Frequency in Prediction Head ACL 2023 Transformers learn through gradual rank increase NeurIPS 2023 Traversing Between Modes in Function Space for Fast Ensembling ICML 2023