softmax approximation

Adaptive Sampling for Efficient Softmax Approximation NeurIPS 2024 A Fresh Take on Stale Embeddings: Improving Dense Retriever Training with Corrector Networks ICML 2024 Optimized Speculative Sampling for GPU Hardware Accelerators EMNLP 2024 Improving Dual-Encoder Training through Dynamic Indexes for Negative Mining AISTATS 2023 SAL-ViT: Towards Latency Efficient Private Inference on ViT using Selective Attention Search with a Learnable Softmax Approximation ICCV 2023 Listwise Learning to Rank Based on Approximate Rank Indicators AAAI 2022 Self-Normalized Importance Sampling for Neural Language Modeling Interspeech 2022 Random Feature Attention ICLR 2021 Successive Halving Top-k Operator AAAI 2021 Learning to Screen for Fast Softmax Inference on Large Vocabulary Neural Networks ICLR 2019 Navigating with Graph Representations for Fast and Scalable Decoding of Neural Language Models NeurIPS 2018 An experimental analysis of Noise-Contrastive Estimation: the noise distribution matters EACL 2017 Efficient softmax approximation for GPUs ICML 2017 SVD-Softmax: Fast Softmax Approximation on Large Vocabulary Neural Networks NeurIPS 2017