← Optimization & Theory
Deep Learning › Optimization & Theory ›

Efficient Computing

1253 directly classified papers

Papers per year

Papers

AMP: Automatically Finding Model Parallel Strategies with Heterogeneity Awareness NIPS 2022
Leveraging Inter-Layer Dependency for Post -Training Quantization NIPS 2022
Spatial Pruned Sparse Convolution for Efficient 3D Object Detection NIPS 2022
Non-deep Networks NIPS 2022
RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer NIPS 2022
Path Independent Equilibrium Models Can Better Exploit Test-Time Computation NIPS 2022
Squeezeformer: An Efficient Transformer for Automatic Speech Recognition NIPS 2022
Toward Robust Spiking Neural Network Against Adversarial Perturbation NIPS 2022
EcoFormer: Energy-Saving Attention with Linear Complexity NIPS 2022
TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasets NIPS 2022
Tempo: Accelerating Transformer-Based Model Training through Memory Footprint Reduction NIPS 2022
EfficientFormer: Vision Transformers at MobileNet Speed NIPS 2022
Efficient Dataset Distillation using Random Feature Approximation NIPS 2022
FP8 Quantization: The Power of the Exponent NIPS 2022
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness NIPS 2022
Confident Adaptive Language Modeling NIPS 2022
DataMUX: Data Multiplexing for Neural Networks NIPS 2022
SAPipe: Staleness-Aware Pipeline for Data Parallel DNN Training NIPS 2022
Quantized Training of Gradient Boosting Decision Trees NIPS 2022
Algorithms that Approximate Data Removal: New Results and Limitations NIPS 2022
Memory safe computations with XLA compiler NIPS 2022
Practical Adversarial Attacks on Spatiotemporal Traffic Forecasting Models NIPS 2022
Efficient learning of nonlinear prediction models with time-series privileged information NIPS 2022
Fine-tuning Language Models over Slow Networks using Activation Quantization with Guarantees NIPS 2022
Wavelet Feature Maps Compression for Image-to-Image CNNs NIPS 2022