conftrace_

memory footprint

21 papers

Explore in graph

Co-occurring keywords

model compression (3302) memory efficiency (261) inference speed (96) convolutional neural network (4226) streaming algorithm (131) deep learning (2118) network pruning (183) model quantization (281) post-training quantization (131) low-bit representation (3)

Papers

Stepping Forward on the Last Mile NIPS 2024
QTIP: Quantization with Trellises and Incoherence Processing NIPS 2024
Resource-Efficient Neural Networks for Embedded Systems JMLR 2024
Activation Map Compression through Tensor Decomposition for Deep Learning NIPS 2024
Pit One Against Many: Leveraging Attention-head Embeddings for Parameter-efficient Multi-head Attention EMNLP 2023
Few-bit Backward: Quantized Gradients of Activation Functions for Memory Footprint Reduction ICML 2023
MotionDeltaCNN: Sparse CNN Inference of Frame Differences in Moving Camera Videos with Spherical Buffers and Padded Convolutions ICCV 2023
Small Footprint Neural Networks for Acoustic Direction of Arrival Estimation INTERSPEECH 2022
Understanding and Overcoming the Challenges of Efficient Transformer Quantization EMNLP 2021
Quadtree Generating Networks: Efficient Hierarchical Scene Parsing with Sparse Convolutions WACV 2020
Online MAP Inference of Determinantal Point Processes NIPS 2020
ASAP: Architecture Search, Anneal and Prune AISTATS 2020
Masking as an Efficient Alternative to Finetuning for Pretrained Language Models EMNLP 2020
Near-Lossless Binarization of Word Embeddings AAAI 2019
Submodular Streaming in All Its Glory: Tight Approximation, Minimum Memory and Low Adaptive Complexity ICML 2019
Adaptive Attention Span in Transformers ACL 2019
Practical Deep Stereo (PDS): Toward applications-friendly deep stereo matching NIPS 2018
PRETZEL: Opening the Black Box of Machine Learning Prediction Serving Systems OSDI 2018
On the Importance of Efficient Transition Modeling for Speaker Diarization INTERSPEECH 2016
Persistent RNNs: Stashing Recurrent Weights On-Chip ICML 2016
Scaling Graph-based Semi Supervised Learning to Large Number of Labels Using Count-Min Sketch AISTATS 2014